Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca94eebda3fba945dcb950f2383051862f70e81ed7744a925d8e8dca7de98820
+oid sha256:89a13628542afba5ec72eb88e32e57dddd8339febe86bc64516da6949b5b5431
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ed2d7a1ef73fd34b9d31e632f5e4e7fac9c28b2a8996beeed01ad95512ac26
+oid sha256:c48d3f3db5649d552ae0ca88698e2dc56ed7220198e7190ee9b6866e6ec82286
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c4e847a39c7cda60a18548b5caed8f2d51e487531e4921dce4c52864b6a86c
+oid sha256:c0ced213fdb7e5dc8bbcba0ba6e029ee11f3e0601fbaaa73e765904952c30b13
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7da45a4da2c8e1739311e34e40c65cf5ebeaf174a3acc39f77ab8ffb56a64d7
+oid sha256:ec42011d56b23afadd97cf881010440b836d197c70acc6e86b8c619d9788beae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dab630d6cc2f6a7b7d1ae39baedfbc813f6ae4102d1d7f0fceb6612b48612d
+oid sha256:08c63f4b77db3d2a5c530e3cc0219dc69ec6964da43fed5769632a47b5f2baf4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44ddbe15dabe88f011046e3ead4bd6d58675384fe6ff9befe7dead6962f74e6
+oid sha256:9b49c3204136e51209e4d10fe258ca78fe300ed1da4fce9b360e5b6aa61cc882
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06483507577599482,
+  "epoch": 0.12967015155198963,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 16.711,
       "eval_steps_per_second": 4.345,
       "step": 25
+    },
+    {
+      "epoch": 0.0674284788070346,
+      "grad_norm": 2.245666027069092,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.9542,
+      "step": 26
+    },
+    {
+      "epoch": 0.0700218818380744,
+      "grad_norm": 2.495150327682495,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 22.7943,
+      "step": 27
+    },
+    {
+      "epoch": 0.07261528486911419,
+      "grad_norm": 5.698614120483398,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 21.7896,
+      "step": 28
+    },
+    {
+      "epoch": 0.07520868790015399,
+      "grad_norm": 2.336207628250122,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 21.5082,
+      "step": 29
+    },
+    {
+      "epoch": 0.07780209093119378,
+      "grad_norm": 2.5703125,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 21.471,
+      "step": 30
+    },
+    {
+      "epoch": 0.08039549396223357,
+      "grad_norm": 2.6710410118103027,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 20.4586,
+      "step": 31
+    },
+    {
+      "epoch": 0.08298889699327336,
+      "grad_norm": 4.7911577224731445,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 20.3356,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558230002431315,
+      "grad_norm": 4.238884449005127,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 20.3566,
+      "step": 33
+    },
+    {
+      "epoch": 0.08817570305535295,
+      "grad_norm": 5.177294731140137,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 18.6525,
+      "step": 34
+    },
+    {
+      "epoch": 0.09076910608639274,
+      "grad_norm": 12.911054611206055,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 20.2838,
+      "step": 35
+    },
+    {
+      "epoch": 0.09336250911743253,
+      "grad_norm": 12.930082321166992,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 18.3263,
+      "step": 36
+    },
+    {
+      "epoch": 0.09595591214847232,
+      "grad_norm": 25.74271583557129,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 22.8791,
+      "step": 37
+    },
+    {
+      "epoch": 0.09854931517951211,
+      "grad_norm": 34.659881591796875,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 30.3727,
+      "step": 38
+    },
+    {
+      "epoch": 0.1011427182105519,
+      "grad_norm": 2.5501174926757812,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 22.6031,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037361212415917,
+      "grad_norm": 2.4213063716888428,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 21.1229,
+      "step": 40
+    },
+    {
+      "epoch": 0.1063295242726315,
+      "grad_norm": 2.5548298358917236,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 21.2577,
+      "step": 41
+    },
+    {
+      "epoch": 0.10892292730367129,
+      "grad_norm": 2.662020444869995,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 19.982,
+      "step": 42
+    },
+    {
+      "epoch": 0.11151633033471108,
+      "grad_norm": 2.9611172676086426,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 19.9527,
+      "step": 43
+    },
+    {
+      "epoch": 0.11410973336575087,
+      "grad_norm": 3.3587005138397217,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 20.605,
+      "step": 44
+    },
+    {
+      "epoch": 0.11670313639679067,
+      "grad_norm": 4.042972564697266,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 20.2018,
+      "step": 45
+    },
+    {
+      "epoch": 0.11929653942783046,
+      "grad_norm": 6.196686267852783,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.2586,
+      "step": 46
+    },
+    {
+      "epoch": 0.12188994245887025,
+      "grad_norm": 6.514049530029297,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 18.7964,
+      "step": 47
+    },
+    {
+      "epoch": 0.12448334548991004,
+      "grad_norm": 7.355401515960693,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 16.1672,
+      "step": 48
+    },
+    {
+      "epoch": 0.12707674852094983,
+      "grad_norm": 16.38075065612793,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 21.551,
+      "step": 49
+    },
+    {
+      "epoch": 0.12967015155198963,
+      "grad_norm": 29.17719078063965,
+      "learning_rate": 1e-05,
+      "loss": 23.2512,
+      "step": 50
+    },
+    {
+      "epoch": 0.12967015155198963,
+      "eval_loss": 0.7126892805099487,
+      "eval_runtime": 3.0304,
+      "eval_samples_per_second": 16.5,
+      "eval_steps_per_second": 4.29,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.633686873758761e+17,
+  "total_flos": 5.2690172274907546e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null