Training in progress, step 2404, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fd6b0054d1f056bdd1f068136faf6ae936a9917ce75d20eb97a5588d22cf17
+oid sha256:87f85bed44e9318e852ba7f17efe6282052cb7b32f2aa95c64b2e71e72a3a8f6
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978241794f0765cf1904aaf145ce5b4c824548d741ec93437d45849535a4ab04
+oid sha256:0a97536a6cd849dbc37c17bc14c1751f38c23bab08204bdfbfe2b1a75da08ad1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79bcfaf683538279e39272f16342dfc788f3ded86099a7f67e3c0cbc2e642c8
+oid sha256:a2ad5e4b3f643cc8277d6ec1988fa3ef711691975814d2464a77f58b0a264633
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6c69dd439a3fb69dcb9250bb4485f8f30f907b01e32d0bd8204147e7413181
+oid sha256:f209df7f5c086a9893a7b6f5e2441e84040cb50d6f1d1fedbaf8d0eb7427609e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.288575142621994,
   "best_model_checkpoint": "./fine-tuned/checkpoint-2000",
-  "epoch": 3.3250207813798838,
+  "epoch": 3.99667497921862,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2404,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,94 @@
       "eval_samples_per_second": 12.873,
       "eval_steps_per_second": 1.616,
       "step": 2000
+    },
+    {
+      "epoch": 3.408146300914381,
+      "grad_norm": 48414.92578125,
+      "learning_rate": 7.362728785357738e-06,
+      "loss": 0.3053,
+      "step": 2050
+    },
+    {
+      "epoch": 3.491271820448878,
+      "grad_norm": 56748.72265625,
+      "learning_rate": 6.32279534109817e-06,
+      "loss": 0.3253,
+      "step": 2100
+    },
+    {
+      "epoch": 3.491271820448878,
+      "eval_loss": 0.28712254762649536,
+      "eval_runtime": 38.3593,
+      "eval_samples_per_second": 12.878,
+      "eval_steps_per_second": 1.616,
+      "step": 2100
+    },
+    {
+      "epoch": 3.574397339983375,
+      "grad_norm": 52447.25390625,
+      "learning_rate": 5.282861896838603e-06,
+      "loss": 0.3188,
+      "step": 2150
+    },
+    {
+      "epoch": 3.657522859517872,
+      "grad_norm": 47730.953125,
+      "learning_rate": 4.242928452579035e-06,
+      "loss": 0.3041,
+      "step": 2200
+    },
+    {
+      "epoch": 3.657522859517872,
+      "eval_loss": 0.2862567901611328,
+      "eval_runtime": 38.2735,
+      "eval_samples_per_second": 12.907,
+      "eval_steps_per_second": 1.62,
+      "step": 2200
+    },
+    {
+      "epoch": 3.7406483790523692,
+      "grad_norm": 48164.21484375,
+      "learning_rate": 3.2029950083194676e-06,
+      "loss": 0.3013,
+      "step": 2250
+    },
+    {
+      "epoch": 3.8237738985868663,
+      "grad_norm": 44376.41015625,
+      "learning_rate": 2.1630615640599005e-06,
+      "loss": 0.3166,
+      "step": 2300
+    },
+    {
+      "epoch": 3.8237738985868663,
+      "eval_loss": 0.2858003079891205,
+      "eval_runtime": 38.3193,
+      "eval_samples_per_second": 12.892,
+      "eval_steps_per_second": 1.618,
+      "step": 2300
+    },
+    {
+      "epoch": 3.9068994181213634,
+      "grad_norm": 53910.06640625,
+      "learning_rate": 1.1231281198003328e-06,
+      "loss": 0.3034,
+      "step": 2350
+    },
+    {
+      "epoch": 3.9900249376558605,
+      "grad_norm": 36512.5546875,
+      "learning_rate": 8.319467554076539e-08,
+      "loss": 0.2983,
+      "step": 2400
+    },
+    {
+      "epoch": 3.9900249376558605,
+      "eval_loss": 0.2859017550945282,
+      "eval_runtime": 38.2723,
+      "eval_samples_per_second": 12.908,
+      "eval_steps_per_second": 1.62,
+      "step": 2400
     }
   ],
   "logging_steps": 50,
@@ -461,12 +549,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.948482562424832e+16,
+  "total_flos": 2.342112942882816e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null