Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84a1c3fd09840b330b4e6148b19233e57ab7e28d1107fbea390f194e791c85a
+oid sha256:fe1268771560fe4054985ba533e0d8e1265cb68e494e6838eb647fc9edb702fe
 size 109086416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c69ab6c7c43404b32c0d81a3f55aa1b31d1dda9ce4b27368d12c37df2d45596
-size 218260474
+oid sha256:528c8e3d78412132b11bbbba1ab1ff9a9185cd6b58e563de0069b7b6eb0374bc
+size 218260730

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c614239c6b794b3509f1055a978743e1c577acc4b56344f3f8a936b9e007322
+oid sha256:54d1167478c538418dde090909f0f0a092d6eae3b53af5e2553aef643b517032
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf3f6bd180530dae464306eed40f7f9105f383e93a2455300d6e6a777764151
+oid sha256:52173b10baaccdab50345561c45a5209e7b1946a31fefd1529f3955468effd15
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7107303142547607,
-  "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-250",
-  "epoch": 0.4,
+  "best_metric": 1.6987907886505127,
+  "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-500",
+  "epoch": 0.8,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,81 @@
       "eval_samples_per_second": 20.019,
       "eval_steps_per_second": 5.005,
       "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.062972903251648,
+      "learning_rate": 9.565616251143094e-05,
+      "loss": 1.7174,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 1.7235748767852783,
+      "eval_runtime": 4.9773,
+      "eval_samples_per_second": 20.091,
+      "eval_steps_per_second": 5.023,
+      "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8863743543624878,
+      "learning_rate": 9.372679583072762e-05,
+      "loss": 1.7156,
+      "step": 350
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.705377459526062,
+      "eval_runtime": 4.9832,
+      "eval_samples_per_second": 20.067,
+      "eval_steps_per_second": 5.017,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1850109100341797,
+      "learning_rate": 9.147119497580047e-05,
+      "loss": 1.7013,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.7099401950836182,
+      "eval_runtime": 4.9875,
+      "eval_samples_per_second": 20.05,
+      "eval_steps_per_second": 5.013,
+      "step": 400
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.9806734323501587,
+      "learning_rate": 8.890618839401924e-05,
+      "loss": 1.6887,
+      "step": 450
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.6758233308792114,
+      "eval_runtime": 4.9812,
+      "eval_samples_per_second": 20.075,
+      "eval_steps_per_second": 5.019,
+      "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8731200695037842,
+      "learning_rate": 8.605091292786664e-05,
+      "loss": 1.6963,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.6987907886505127,
+      "eval_runtime": 4.9844,
+      "eval_samples_per_second": 20.063,
+      "eval_steps_per_second": 5.016,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -101,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.426173265267917e+16,
+  "total_flos": 1.2852129603531571e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null