Training in progress, step 1875, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73dcc728bd3117c3ddcb580ef3f1b393dfb729105f5e1d2fdab99854f2758874
+oid sha256:6a3668c48907d6be9c34a6d02741c3750faabcfd1d5a6333cafe608af5a229ae
 size 109086416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446a3af6fdee1a0dd1551c20907478e105e6522c7cc9df77f10f1fae6b402ec6
+oid sha256:38c90ddf4352401e02b05f9c5ac779323fe0e9cba9deb1ed0ba3fadee738b6bc
 size 218260730

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1fc5a9c9f608c99649f2e480872fa8be5ea1043623c84a23661e662266b584
+oid sha256:a4d45a4286ba74a8054247c8bb988cbde8153b7096a421868e4e6e75e1d96fe8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f70d0c9a1f2ec5616d0ea31f304bbe8c20a9687c5c28d05c761302a0b97133f
+oid sha256:69b45defeb8acd40b1f654b531ab2159e89f65aca484da94094d0271343bc0bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.675691843032837,
   "best_model_checkpoint": "Pricer-FineTune-OpenSource-2024-10-23_08.48.15/checkpoint-1250",
-  "epoch": 2.8,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 1750,
+  "global_step": 1875,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,36 @@
       "eval_samples_per_second": 20.045,
       "eval_steps_per_second": 5.011,
       "step": 1750
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 3.2328884601593018,
+      "learning_rate": 4.1934023124329257e-07,
+      "loss": 1.4583,
+      "step": 1800
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 1.7641412019729614,
+      "eval_runtime": 4.9803,
+      "eval_samples_per_second": 20.079,
+      "eval_steps_per_second": 5.02,
+      "step": 1800
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 4.39493465423584,
+      "learning_rate": 4.665137700333166e-08,
+      "loss": 1.4495,
+      "step": 1850
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 1.765012502670288,
+      "eval_runtime": 4.9788,
+      "eval_samples_per_second": 20.085,
+      "eval_steps_per_second": 5.021,
+      "step": 1850
     }
   ],
   "logging_steps": 50,
@@ -546,12 +576,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.4981043586832794e+17,
+  "total_flos": 4.819416637396746e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null