Upload 38 files

adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afb2e240f8bfd24de69006796dd2addb199ad28c207c55c7fa41e3448bf6b29
+size 16800753

checkpoint-200/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2733556a0a6f6116f3701dd7d70ce4912b0ca30ca22884dff494ba1887de9877
+size 16800753

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a1a995b82024c59a5befce2720f52d261a25b604993b8c646570a35340918b
+size 33608197

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc126f9cef6ecb915cd3065b8c33f9538d8dae1eb653025d259a590b6ff29613
+size 18679

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d8fbcdf4dcf2743c470a34a162683df5443b8dd1c333316dbcb36be85a6191
+size 18679

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea7384a66aa6d9ed75fff0b41856eef1e475f9c36dca9acb13cbdf12bbfd025
+size 18679

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6e1235a6dacf38d6fbb8193d2c827ef768b991f7c802b154e9170f9b5b7b26
+size 18679

checkpoint-200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5fe5095aa2d75e06f443dbfa60f000ba80d149558e8f0de06acd4e8882d920
+size 18679

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
+size 557

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541dca843bbd76c64cb97c112d657f071d35e254ae28f1849b22358f3024b6fb
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 1.9148070812225342,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-200",
+  "epoch": 0.9153318077803204,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.6041,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 3.462,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 3.0984,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.5603,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.2705,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.2129,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.1456,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.0951,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.0716,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.0437,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 1.9825,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 1.9807,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 1.9581,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.947,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 1.9234,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 1.9434,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 1.8722,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.8902,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.8855,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 1.9148070812225342,
+      "eval_runtime": 83.9113,
+      "eval_samples_per_second": 23.835,
+      "eval_steps_per_second": 0.596,
+      "step": 200
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 2.0917978937688064e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3656c96b532a223580bc4d06721b750f52dbf6634f65bed7bd19dac80fd17ec8
+size 3963

checkpoint-400/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-400/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e89c7e86fdf9387851fe9dc398361390baad426bbbea175402da013093b3f8
+size 16800753

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5f7e23c8687c063e97dcbc872cd5c540e1644cb6b79fadcec8fb9da0798d22
+size 33608197

checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b769f21c8555d61f45c04c0633f3fe86a6054248deedf0af918ee82dc1723ec8
+size 18679

checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d33f763302acb7364215fb933d3ac9478ebcdbcc3974e251b4425bd694a73d
+size 18679

checkpoint-400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14df554899870904d42ff76156c432f0c6daa6cad85a35e24f329dd4b9fd59ea
+size 18679

checkpoint-400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f472acfb4b212a62a2d0f676cc40cbc63f8284c2d0835c0d3bd9980cc1980616
+size 18679

checkpoint-400/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cb0dbb305e72cd7f9ddf1bad86126c6460e6852d885de1d16c93303d780b35
+size 18679

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
+size 557

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900a5ec23049aed4393fb57e3dccd03b426335b20c3b0fae68ba3491c2114549
+size 627

checkpoint-400/trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 1.8361974954605103,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-400",
+  "epoch": 1.8306636155606406,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.6041,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 3.462,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 3.0984,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.5603,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.2705,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.2129,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.1456,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.0951,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.0716,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.0437,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 1.9825,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 1.9807,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 1.9581,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.947,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 1.9234,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 1.9434,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 1.8722,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.8902,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.8855,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 1.9148070812225342,
+      "eval_runtime": 83.9113,
+      "eval_samples_per_second": 23.835,
+      "eval_steps_per_second": 0.596,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00024043321299638986,
+      "loss": 1.9064,
+      "step": 210
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00023501805054151624,
+      "loss": 1.9195,
+      "step": 220
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00022960288808664258,
+      "loss": 1.875,
+      "step": 230
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00022418772563176893,
+      "loss": 1.8733,
+      "step": 240
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002187725631768953,
+      "loss": 1.8652,
+      "step": 250
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00021335740072202166,
+      "loss": 1.8704,
+      "step": 260
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00020794223826714798,
+      "loss": 1.8524,
+      "step": 270
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020252707581227435,
+      "loss": 1.8322,
+      "step": 280
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001971119133574007,
+      "loss": 1.8383,
+      "step": 290
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019169675090252705,
+      "loss": 1.846,
+      "step": 300
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00018628158844765343,
+      "loss": 1.8283,
+      "step": 310
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00018086642599277977,
+      "loss": 1.8369,
+      "step": 320
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00017545126353790612,
+      "loss": 1.8398,
+      "step": 330
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00017003610108303247,
+      "loss": 1.8203,
+      "step": 340
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00016462093862815885,
+      "loss": 1.8132,
+      "step": 350
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001592057761732852,
+      "loss": 1.7873,
+      "step": 360
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015379061371841152,
+      "loss": 1.8322,
+      "step": 370
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001483754512635379,
+      "loss": 1.809,
+      "step": 380
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00014296028880866424,
+      "loss": 1.8377,
+      "step": 390
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00013754512635379062,
+      "loss": 1.8083,
+      "step": 400
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 1.8361974954605103,
+      "eval_runtime": 81.4531,
+      "eval_samples_per_second": 24.554,
+      "eval_steps_per_second": 0.614,
+      "step": 400
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 4.187774006885089e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3656c96b532a223580bc4d06721b750f52dbf6634f65bed7bd19dac80fd17ec8
+size 3963

checkpoint-600/adapter_model/adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-600/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d284218c118b67af53d1153d7d9b765c54e65b1f21f5c25ff9a5ae93cfd07f06
+size 16800753

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a8cc72530101b7900b3866900784aa50673accef112b87244730f2beee7d5a
+size 33608197

checkpoint-600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc42efe1015d0a1f4d1e485fbd41a0b6fd8036aa69fef8788f2c90562c97c1a0
+size 18679

checkpoint-600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e19c2c9082d555a3703d473c07396c18cd8694fb3c8d7320ef8f43b3e504d0
+size 18679

checkpoint-600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992a37055b1cd2d5dc2e1b39006ee12a6fa88f5aadb9e464a629e5cb231003a7
+size 18679

checkpoint-600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8959fc8658f3a311bffedc0f99ad485234c46d54e67db23e9caaf68e67cfc599
+size 18679

checkpoint-600/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0128a0427dcf1b4476c54d5fce77d60b976360a22e719def9a5b88365d618c8d
+size 18679

checkpoint-600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc9eacfeb00bd0bfeb98934a2309be01be65b288e0d747bbfc423b32679169f
+size 557

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926c30c8e047c3e78553036f231b6fc7cd2b592198516d3ee1e0875dff68cacf
+size 627

checkpoint-600/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_metric": 1.8054813146591187,
+  "best_model_checkpoint": "./lora-redpajama/checkpoint-600",
+  "epoch": 2.745995423340961,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.6041,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 3.462,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 3.0984,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.5603,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015,
+      "loss": 2.2705,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.2129,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 2.1456,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 2.0951,
+      "step": 80
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00027,
+      "loss": 2.0716,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 2.0437,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002945848375451263,
+      "loss": 1.9825,
+      "step": 110
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00028916967509025267,
+      "loss": 2.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000283754512635379,
+      "loss": 1.9807,
+      "step": 130
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027833935018050537,
+      "loss": 1.9581,
+      "step": 140
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027292418772563177,
+      "loss": 1.947,
+      "step": 150
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002675090252707581,
+      "loss": 1.9234,
+      "step": 160
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026209386281588447,
+      "loss": 1.9434,
+      "step": 170
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002566787003610108,
+      "loss": 1.8722,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025126353790613716,
+      "loss": 1.8902,
+      "step": 190
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002458483754512635,
+      "loss": 1.8855,
+      "step": 200
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 1.9148070812225342,
+      "eval_runtime": 83.9113,
+      "eval_samples_per_second": 23.835,
+      "eval_steps_per_second": 0.596,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00024043321299638986,
+      "loss": 1.9064,
+      "step": 210
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00023501805054151624,
+      "loss": 1.9195,
+      "step": 220
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00022960288808664258,
+      "loss": 1.875,
+      "step": 230
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00022418772563176893,
+      "loss": 1.8733,
+      "step": 240
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002187725631768953,
+      "loss": 1.8652,
+      "step": 250
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00021335740072202166,
+      "loss": 1.8704,
+      "step": 260
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00020794223826714798,
+      "loss": 1.8524,
+      "step": 270
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020252707581227435,
+      "loss": 1.8322,
+      "step": 280
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001971119133574007,
+      "loss": 1.8383,
+      "step": 290
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019169675090252705,
+      "loss": 1.846,
+      "step": 300
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00018628158844765343,
+      "loss": 1.8283,
+      "step": 310
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00018086642599277977,
+      "loss": 1.8369,
+      "step": 320
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00017545126353790612,
+      "loss": 1.8398,
+      "step": 330
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00017003610108303247,
+      "loss": 1.8203,
+      "step": 340
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00016462093862815885,
+      "loss": 1.8132,
+      "step": 350
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001592057761732852,
+      "loss": 1.7873,
+      "step": 360
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015379061371841152,
+      "loss": 1.8322,
+      "step": 370
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001483754512635379,
+      "loss": 1.809,
+      "step": 380
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00014296028880866424,
+      "loss": 1.8377,
+      "step": 390
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00013754512635379062,
+      "loss": 1.8083,
+      "step": 400
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 1.8361974954605103,
+      "eval_runtime": 81.4531,
+      "eval_samples_per_second": 24.554,
+      "eval_steps_per_second": 0.614,
+      "step": 400
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013212996389891696,
+      "loss": 1.8169,
+      "step": 410
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001267148014440433,
+      "loss": 1.7913,
+      "step": 420
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00012129963898916966,
+      "loss": 1.7949,
+      "step": 430
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00011588447653429602,
+      "loss": 1.7821,
+      "step": 440
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00011046931407942237,
+      "loss": 1.7765,
+      "step": 450
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00010505415162454872,
+      "loss": 1.7977,
+      "step": 460
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.963898916967508e-05,
+      "loss": 1.7647,
+      "step": 470
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.422382671480144e-05,
+      "loss": 1.7766,
+      "step": 480
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.880866425992779e-05,
+      "loss": 1.78,
+      "step": 490
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.339350180505415e-05,
+      "loss": 1.7828,
+      "step": 500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 7.797833935018049e-05,
+      "loss": 1.7468,
+      "step": 510
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 7.256317689530685e-05,
+      "loss": 1.7982,
+      "step": 520
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.71480144404332e-05,
+      "loss": 1.7885,
+      "step": 530
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 6.173285198555956e-05,
+      "loss": 1.7629,
+      "step": 540
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.6317689530685916e-05,
+      "loss": 1.7515,
+      "step": 550
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.090252707581227e-05,
+      "loss": 1.731,
+      "step": 560
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.548736462093862e-05,
+      "loss": 1.7954,
+      "step": 570
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 4.007220216606498e-05,
+      "loss": 1.7446,
+      "step": 580
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 3.4657039711191336e-05,
+      "loss": 1.7634,
+      "step": 590
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.9241877256317685e-05,
+      "loss": 1.7523,
+      "step": 600
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.8054813146591187,
+      "eval_runtime": 79.1242,
+      "eval_samples_per_second": 25.277,
+      "eval_steps_per_second": 0.632,
+      "step": 600
+    }
+  ],
+  "max_steps": 654,
+  "num_train_epochs": 3,
+  "total_flos": 6.284389017861489e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3656c96b532a223580bc4d06721b750f52dbf6634f65bed7bd19dac80fd17ec8
+size 3963