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:f99bc2c659cbdb0992e1a6091af6809085d19bc2edf14ae50e83db113fa5fcb4
+oid sha256:59ed42b88d87af894769812b274e21e14ffccb5c177cb139cbcfd7034a0c6545
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a69589c53894362eff20f58966ceb7c4fe896fd6b42431e73043324550d40fb
+oid sha256:c1cf4bc8d78382435084c4ca4e9a3051ba92da347a7dfa2c6faeb6f1913ef2db
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080926b6fad49ee6b44ff32b6c88dcf1a54560ba5269dd472628f349a0e91734
+oid sha256:f54a4529a8e6845ded0eda45072a4e815479439591a260f73506331363d14828
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e6f18cc73c49e1b8ffd8c02656630b4c1ab425d84004ddab33c7d1ac32ba3f
+oid sha256:1122e23e5053dc11adc18506adea02f4afa189a4981884a78b8091004698e3c9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a884ce65b2106c5faada4bc542ca8806b383884d40a67a36a96d4d9a59de34ad
+oid sha256:9672115f995075c45b19e844719708bc3519b7f8900dabf0e3b2c0ab349455b1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1601b0f6af9e056067f5465ae47446902063858add4122d3355cea2b50d7a490
+oid sha256:f80273d0fe6205387d305a36fe3d9d7805a1c74392ec5a9b45ad7c4825c5914c
 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": 0.006670947191114298,
+  "epoch": 0.013341894382228596,
   "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": 16.94,
       "eval_steps_per_second": 4.404,
       "step": 25
+    },
+    {
+      "epoch": 0.00693778507875887,
+      "grad_norm": 14.102134704589844,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 85.3265,
+      "step": 26
+    },
+    {
+      "epoch": 0.0072046229664034424,
+      "grad_norm": 16.71866798400879,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 86.5452,
+      "step": 27
+    },
+    {
+      "epoch": 0.007471460854048014,
+      "grad_norm": 18.847749710083008,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 86.1274,
+      "step": 28
+    },
+    {
+      "epoch": 0.007738298741692586,
+      "grad_norm": 17.256502151489258,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 85.8048,
+      "step": 29
+    },
+    {
+      "epoch": 0.008005136629337158,
+      "grad_norm": 10.483077049255371,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 86.754,
+      "step": 30
+    },
+    {
+      "epoch": 0.00827197451698173,
+      "grad_norm": 7.900310039520264,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 84.7266,
+      "step": 31
+    },
+    {
+      "epoch": 0.008538812404626303,
+      "grad_norm": 10.001039505004883,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 85.7117,
+      "step": 32
+    },
+    {
+      "epoch": 0.008805650292270874,
+      "grad_norm": 15.488116264343262,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 84.1797,
+      "step": 33
+    },
+    {
+      "epoch": 0.009072488179915445,
+      "grad_norm": 20.616697311401367,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 85.459,
+      "step": 34
+    },
+    {
+      "epoch": 0.009339326067560017,
+      "grad_norm": 25.470232009887695,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 83.8137,
+      "step": 35
+    },
+    {
+      "epoch": 0.00960616395520459,
+      "grad_norm": 34.425106048583984,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 87.1356,
+      "step": 36
+    },
+    {
+      "epoch": 0.009873001842849161,
+      "grad_norm": 74.32858276367188,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 89.267,
+      "step": 37
+    },
+    {
+      "epoch": 0.010139839730493733,
+      "grad_norm": 67.69532012939453,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 99.5797,
+      "step": 38
+    },
+    {
+      "epoch": 0.010406677618138306,
+      "grad_norm": 6.894927978515625,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 83.4439,
+      "step": 39
+    },
+    {
+      "epoch": 0.010673515505782877,
+      "grad_norm": 7.002964496612549,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 84.3967,
+      "step": 40
+    },
+    {
+      "epoch": 0.010940353393427448,
+      "grad_norm": 6.538271903991699,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 85.0133,
+      "step": 41
+    },
+    {
+      "epoch": 0.011207191281072022,
+      "grad_norm": 7.0363383293151855,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 84.4411,
+      "step": 42
+    },
+    {
+      "epoch": 0.011474029168716593,
+      "grad_norm": 7.243854522705078,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 85.7455,
+      "step": 43
+    },
+    {
+      "epoch": 0.011740867056361164,
+      "grad_norm": 6.435781478881836,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 84.7364,
+      "step": 44
+    },
+    {
+      "epoch": 0.012007704944005737,
+      "grad_norm": 7.823002338409424,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 83.3252,
+      "step": 45
+    },
+    {
+      "epoch": 0.012274542831650309,
+      "grad_norm": 8.64023494720459,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 83.6382,
+      "step": 46
+    },
+    {
+      "epoch": 0.01254138071929488,
+      "grad_norm": 7.904877185821533,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 84.5418,
+      "step": 47
+    },
+    {
+      "epoch": 0.012808218606939453,
+      "grad_norm": 10.810150146484375,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 85.2486,
+      "step": 48
+    },
+    {
+      "epoch": 0.013075056494584025,
+      "grad_norm": 17.670724868774414,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 87.8722,
+      "step": 49
+    },
+    {
+      "epoch": 0.013341894382228596,
+      "grad_norm": 50.694305419921875,
+      "learning_rate": 1e-05,
+      "loss": 99.3798,
+      "step": 50
+    },
+    {
+      "epoch": 0.013341894382228596,
+      "eval_loss": 2.659498691558838,
+      "eval_runtime": 2.9744,
+      "eval_samples_per_second": 16.81,
+      "eval_steps_per_second": 4.371,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null