Training in progress, step 1250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213054c4927c6f3bca1e8082d827c430bb295745b32b92115688f61434f7f075
+oid sha256:e7dddb739a4b3f72e2fe01917ea31953f599c57b6e9342cc1fd8b9e23e5323bb
 size 109086416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102d67e35bfbcc4b9e815d03b2ae65a3860e14c952cb6a160cddaed2bd9e62df
+oid sha256:de7deff4ffeb1624f5813110d9915b8d594ad08038a97815c81f184bddd8fd3e
 size 218260730

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca646238b9defc5bf2a095179cb788aa143627991f51a70cd39966e3562a2aab
+oid sha256:60f697d3073b12339737b2b698ed791233cd92575a6941075313c4988bdb3838
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199e6824b18b1d9debbd05233cf73ed2bcbb72beea16b10948ab69d09fd868c5
+oid sha256:93259b1959c21b6476783839a426aba03f7028583f1b66749ef00cd2d3666606
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6910121440887451,
-  "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-750",
-  "epoch": 1.6,
+  "best_metric": 1.675691843032837,
+  "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-1250",
+  "epoch": 2.0,
   "eval_steps": 50,
-  "global_step": 1000,
+  "global_step": 1250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,81 @@
       "eval_samples_per_second": 20.086,
       "eval_steps_per_second": 5.021,
       "step": 1000
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 2.525702714920044,
+      "learning_rate": 4.276765569666291e-05,
+      "loss": 1.616,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "eval_loss": 1.6906436681747437,
+      "eval_runtime": 4.9808,
+      "eval_samples_per_second": 20.077,
+      "eval_steps_per_second": 5.019,
+      "step": 1050
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.1740636825561523,
+      "learning_rate": 3.8525263068401055e-05,
+      "loss": 1.5903,
+      "step": 1100
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 1.6799463033676147,
+      "eval_runtime": 4.9781,
+      "eval_samples_per_second": 20.088,
+      "eval_steps_per_second": 5.022,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 2.1382858753204346,
+      "learning_rate": 3.436848044782893e-05,
+      "loss": 1.583,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "eval_loss": 1.6741628646850586,
+      "eval_runtime": 4.9792,
+      "eval_samples_per_second": 20.084,
+      "eval_steps_per_second": 5.021,
+      "step": 1150
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.8631138801574707,
+      "learning_rate": 3.032832050166239e-05,
+      "loss": 1.5876,
+      "step": 1200
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 1.6653131246566772,
+      "eval_runtime": 4.9832,
+      "eval_samples_per_second": 20.067,
+      "eval_steps_per_second": 5.017,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0618934631347656,
+      "learning_rate": 2.6434925805380144e-05,
+      "loss": 1.5982,
+      "step": 1250
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.675691843032837,
+      "eval_runtime": 4.9832,
+      "eval_samples_per_second": 20.067,
+      "eval_steps_per_second": 5.017,
+      "step": 1250
     }
   ],
   "logging_steps": 50,
@@ -326,7 +401,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5704331516064563e+17,
+  "total_flos": 3.212949245531259e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null