Training in progress, step 50, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3dbfc10c6e5c8d6c41f0cbbbe4dca8baaeedd3114cc8b559f58e96d47ea0f5e
+oid sha256:1bb038a9aa92fa45d9aaabd2236e3c7d97215a54e110c0afb98849299578118c
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee8409081ad1eda489d5e0eea6674e798171d570b3e2ab696109b024ef0265b
+oid sha256:4f4aae276a4d8f9fb822a9e4f697b67666e3e5d61fe21cb70d7431d9eafd2583
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:730152bfc2818de9585c34bf57d2946f7e3fff8d165504f3c76b29261acf1ad3
+oid sha256:21a23643415bc9ed079fe90713e52ecaf079f5939f7f91d82a4b54b3db2d10ac
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282db3f48eeea80db1b61a3cbc785c24d0565776ec27f89654a543833c05c48f
+oid sha256:16332399f14451488556d919f5130e1ff3869a46bdf298eef702a40ecdcaefd7
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97474a95cf2d0e6166f036d8937e33ebebb2adb23cf1177f88edc10dc549c905
+oid sha256:455445cc351d1d9c0932fce6221afb99c553d40bbefe6e459ef4b63ef6e54132
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
+oid sha256:3353489b38799fd56e115bb7a4e2a7a61242a09d303dca9e218c08878b9b8728
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,67 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9523809523809523,
-  "eval_steps": 100,
-  "global_step": 100,
+  "epoch": 0.11848341232227488,
+  "eval_steps": 50,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.009523809523809525,
-      "eval_loss": 1.873080849647522,
-      "eval_runtime": 27.7212,
-      "eval_samples_per_second": 54.146,
-      "eval_steps_per_second": 6.782,
+      "epoch": 0.002369668246445498,
+      "eval_loss": 1.879074215888977,
+      "eval_runtime": 110.3924,
+      "eval_samples_per_second": 13.597,
+      "eval_steps_per_second": 6.803,
       "step": 1
     },
     {
-      "epoch": 0.09523809523809523,
-      "grad_norm": 32.5,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 2.7071,
+      "epoch": 0.023696682464454975,
+      "grad_norm": 48.75,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6549,
       "step": 10
     },
     {
-      "epoch": 0.19047619047619047,
-      "grad_norm": 404.0,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 3.1591,
+      "epoch": 0.04739336492890995,
+      "grad_norm": 22.125,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.7478,
       "step": 20
     },
     {
-      "epoch": 0.2857142857142857,
-      "grad_norm": 166.0,
-      "learning_rate": 0.0002,
-      "loss": 8.2396,
+      "epoch": 0.07109004739336493,
+      "grad_norm": 22.875,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9228,
       "step": 30
     },
     {
-      "epoch": 0.38095238095238093,
-      "grad_norm": 1704.0,
-      "learning_rate": 0.00019984815164333163,
-      "loss": 10.9647,
+      "epoch": 0.0947867298578199,
+      "grad_norm": 30.0,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 2.186,
       "step": 40
     },
     {
-      "epoch": 0.47619047619047616,
-      "grad_norm": 1160.0,
-      "learning_rate": 0.00019939306773179497,
-      "loss": 8.6651,
+      "epoch": 0.11848341232227488,
+      "grad_norm": 30.25,
+      "learning_rate": 8e-05,
+      "loss": 2.7775,
       "step": 50
     },
     {
-      "epoch": 0.5714285714285714,
-      "grad_norm": 13.0625,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 7.7909,
-      "step": 60
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 8.6875,
-      "learning_rate": 0.00019757963826274357,
-      "loss": 7.4806,
-      "step": 70
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 19.875,
-      "learning_rate": 0.00019622680003092503,
-      "loss": 7.4457,
-      "step": 80
-    },
-    {
-      "epoch": 0.8571428571428571,
-      "grad_norm": 10.0625,
-      "learning_rate": 0.00019458172417006347,
-      "loss": 7.3482,
-      "step": 90
-    },
-    {
-      "epoch": 0.9523809523809523,
-      "grad_norm": 11.3125,
-      "learning_rate": 0.00019264940672148018,
-      "loss": 7.1392,
-      "step": 100
-    },
-    {
-      "epoch": 0.9523809523809523,
-      "eval_loss": 7.116525650024414,
-      "eval_runtime": 27.013,
-      "eval_samples_per_second": 55.566,
-      "eval_steps_per_second": 6.96,
-      "step": 100
+      "epoch": 0.11848341232227488,
+      "eval_loss": 2.7163915634155273,
+      "eval_runtime": 110.023,
+      "eval_samples_per_second": 13.643,
+      "eval_steps_per_second": 6.826,
+      "step": 50
     }
   ],
   "logging_steps": 10,
-  "max_steps": 600,
+  "max_steps": 2500,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 6,
   "save_steps": 50,
@@ -112,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.990071085400064e+16,
+  "total_flos": 8737589192294400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802545d1e97192e378ffcd2cad9bce4ceaee2e6e0f16293234288d73f5cc067f
+oid sha256:275470b754135bb198fe3e1b0d3b0332d2114e36c8e4ac84c30e44373e277d5a
 size 6776