Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619e9a53f49dec2566c9a98e6dcb1bed6dc7993d4b7ccf60204a9e6261fe46d2
+oid sha256:45a95787a4f0d59d777f32312df3183e7ca71a9e350b75b0141a40ace6f8527b
 size 57029756

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1d56fc341eab45ea15135984abe110fae89f56f08327c3d2b94ea480b9f4bc
+oid sha256:1460dd019148384f9b0f3ae825901e137507b363f3aaf0a999f0b81babc2b22e
 size 114100410

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a94b7bbebc6d906d53a4da39cdae0c35e24d988bd6807fa9fae222b6c5c145
+oid sha256:da0daaee6d37fe3cce06b6f0665377993b2425570925631e7bd3877098b13e56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a84374ae6db0b004a6b87b94c39a9a830c4ddd474ee1230a71eeead31d62515
+oid sha256:0992f3eb6a6e87d7c905716ad6cb10cdc7e7e02476fe12e47e23d9729391391c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,77 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.847380410022779,
+  "epoch": 0.5694760820045558,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.5694760820045558,
-      "grad_norm": 1.6383419036865234,
-      "learning_rate": 1.6203492786636296e-05,
-      "loss": 0.5069,
+      "grad_norm": 1.5356756448745728,
+      "learning_rate": 1.7722095671981778e-05,
+      "loss": 0.1506,
       "step": 500
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.9481309673217151,
-      "eval_f1": 0.7565174618789966,
-      "eval_loss": 0.21838697791099548,
-      "eval_precision": 0.7395811070741611,
-      "eval_recall": 0.7742476787112652,
-      "eval_runtime": 2.9034,
-      "eval_samples_per_second": 1119.376,
-      "eval_steps_per_second": 70.262,
-      "step": 878
-    },
-    {
-      "epoch": 1.1389521640091116,
-      "grad_norm": 2.9091055393218994,
-      "learning_rate": 1.240698557327259e-05,
-      "loss": 0.2615,
-      "step": 1000
-    },
-    {
-      "epoch": 1.7084282460136673,
-      "grad_norm": 3.3975818157196045,
-      "learning_rate": 8.610478359908885e-06,
-      "loss": 0.2068,
-      "step": 1500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.9593149792682734,
-      "eval_f1": 0.8157792243921438,
-      "eval_loss": 0.16669189929962158,
-      "eval_precision": 0.8114899269426611,
-      "eval_recall": 0.8201141067233472,
-      "eval_runtime": 3.0974,
-      "eval_samples_per_second": 1049.272,
-      "eval_steps_per_second": 65.862,
-      "step": 1756
-    },
-    {
-      "epoch": 2.277904328018223,
-      "grad_norm": 7.613577842712402,
-      "learning_rate": 4.8139711465451785e-06,
-      "loss": 0.1847,
-      "step": 2000
-    },
-    {
-      "epoch": 2.847380410022779,
-      "grad_norm": 3.9789023399353027,
-      "learning_rate": 1.0174639331814731e-06,
-      "loss": 0.166,
-      "step": 2500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2634,
+  "max_steps": 4390,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -85,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52075934697042.0,
+  "total_flos": 10392521743584.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685608d25e53a9d2b788ce2fd83e8fa1c83bb39b307e090b4935f273ce41406f
+oid sha256:6179295ed33670bef4e6ae443db6c86535ebdf6636bdd940a34e8a5e5cd430e0
 size 5304