Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5ec040b12517fdd7deecc06ae8726c116052e27f3cc8dfa3cd5c93c96e7566
+oid sha256:1f79e495154da67b877bea3f63a4a67b50b5bd6dc9f526699f399304facad62e
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebd41dd436d0a96f8f404dd2a9a10c9b7be31469235ba2818e32114795ba445
+oid sha256:d90d453de31c2419e4e349d4a4f435ab05d64a46c66c09d9b10ac7145a578d1f
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9302dd11ca8cf3c2eadc2e2dd7547119f45305e0e26866eb1c66b0a7bf115ba8
+oid sha256:18250a969c7e8b744e0a81968b85799869d2e007063948d0e72541065db3bc16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbc19acf0a0a927f8be2149598258a3f317e7393a952a331dd9a912902ffcc3
+oid sha256:7bdb930721cbebdf735b7bba6276bd5739b55ef721382393eeafb8577701beb4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3724469542503357,
-  "best_model_checkpoint": "results/checkpoint-2000",
-  "epoch": 0.19104021396503965,
+  "best_metric": 0.3715578615665436,
+  "best_model_checkpoint": "results/checkpoint-4000",
+  "epoch": 0.3820804279300793,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,66 @@
       "eval_samples_per_second": 249.181,
       "eval_steps_per_second": 3.897,
       "step": 2000
+    },
+    {
+      "epoch": 0.23880026745629956,
+      "grad_norm": 8.174205780029297,
+      "learning_rate": 4.402999331359251e-05,
+      "loss": 0.4269,
+      "step": 2500
+    },
+    {
+      "epoch": 0.23880026745629956,
+      "eval_loss": 0.3822018504142761,
+      "eval_runtime": 109.3926,
+      "eval_samples_per_second": 239.056,
+      "eval_steps_per_second": 3.739,
+      "step": 2500
+    },
+    {
+      "epoch": 0.28656032094755945,
+      "grad_norm": 8.617950439453125,
+      "learning_rate": 4.2835991976311015e-05,
+      "loss": 0.4417,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28656032094755945,
+      "eval_loss": 0.37791815400123596,
+      "eval_runtime": 110.9874,
+      "eval_samples_per_second": 235.621,
+      "eval_steps_per_second": 3.685,
+      "step": 3000
+    },
+    {
+      "epoch": 0.33432037443881935,
+      "grad_norm": 4.857789993286133,
+      "learning_rate": 4.164199063902952e-05,
+      "loss": 0.4324,
+      "step": 3500
+    },
+    {
+      "epoch": 0.33432037443881935,
+      "eval_loss": 0.37730905413627625,
+      "eval_runtime": 110.4008,
+      "eval_samples_per_second": 236.873,
+      "eval_steps_per_second": 3.705,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3820804279300793,
+      "grad_norm": 4.581517219543457,
+      "learning_rate": 4.044798930174802e-05,
+      "loss": 0.4184,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3820804279300793,
+      "eval_loss": 0.3715578615665436,
+      "eval_runtime": 111.0466,
+      "eval_samples_per_second": 235.496,
+      "eval_steps_per_second": 3.683,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -86,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3685472280576e+16,
+  "total_flos": 6.7370944561152e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null