Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2de3e8a0e43fd8dd9c15b000eeb4f2021cdd5eccb54819b3b0728d1b7267178
+oid sha256:6ef30dc9a100b240120af62823ca4707e4a35c361f060e8d6c15efa77b5e60f1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b82ac85f6bf6ebbbd22442579d6ae1b2c1bf03a31bf32cacfc36ffd617eda63
+oid sha256:12c3c123305a27e77f9affa5e1e0fa48210446cf570c456de0079a60956cc284
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fae9953ba8f56f4659e95c4daffe7b5a7e29fdb6b98008ab375ed9889239ac9
+oid sha256:29621a933fe39840d93ef11565a36bb6ba3b5a377ed5e55e63eb1777b2373cd7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e08cecb96b0575af87573c227caf7ff2501936ebe822db040ebe990bb471ce73
+oid sha256:b929b010a2bf1a7268bbc9d5744f2ae71afa768419f9ef267d54626a2e8ef40d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09038107097148895,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
-  "epoch": 0.12,
+  "best_metric": 0.08910445868968964,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-2000",
+  "epoch": 0.16,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,84 @@
       "eval_samples_per_second": 22.759,
       "eval_steps_per_second": 5.69,
       "step": 1500
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.19083499908447266,
+      "learning_rate": 2.81412e-05,
+      "loss": 0.0736,
+      "step": 1550
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.19123569130897522,
+      "learning_rate": 2.80812e-05,
+      "loss": 0.0766,
+      "step": 1600
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.24691827595233917,
+      "learning_rate": 2.80212e-05,
+      "loss": 0.0798,
+      "step": 1650
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.17910048365592957,
+      "learning_rate": 2.79612e-05,
+      "loss": 0.0687,
+      "step": 1700
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.1740667223930359,
+      "learning_rate": 2.79012e-05,
+      "loss": 0.0758,
+      "step": 1750
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.15178219974040985,
+      "learning_rate": 2.78412e-05,
+      "loss": 0.0732,
+      "step": 1800
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.1904926896095276,
+      "learning_rate": 2.77812e-05,
+      "loss": 0.0734,
+      "step": 1850
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.2795208990573883,
+      "learning_rate": 2.77212e-05,
+      "loss": 0.076,
+      "step": 1900
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.18160228431224823,
+      "learning_rate": 2.76612e-05,
+      "loss": 0.0716,
+      "step": 1950
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.15877611935138702,
+      "learning_rate": 2.76012e-05,
+      "loss": 0.0773,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.08910445868968964,
+      "eval_runtime": 87.8635,
+      "eval_samples_per_second": 22.763,
+      "eval_steps_per_second": 5.691,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -260,7 +338,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3653747343360000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null