Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2968fae491fefd2f9a431c5a0bf13b850a49d5465bf2f3ab25c45e33c0a41886
+oid sha256:20c40f891a6ad2cd6bdb721e2f111292589ff390313316ee8f0d082edb0b9b03
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938bb6b2c29f2be8620725e1d9819dff7d9e79ec433558bbd6ac24951cd0c258
+oid sha256:97e7d057f22cb8197d547d1ed0d192390fd1e34fb36aa35aa6b76f03d0e2f9d9
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb257991d06d0ad08909803a2d396d17f96d7f13a21d29dde85f6747c2c6f53
+oid sha256:fe7c95ba6d299e128ae454cc0731e509722836b2913c0cc0546da0aa648a6383
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c587e6b31550b01ed65ddb502a6dbeb722c15426dc145d4dd3a0afea5fb120
+oid sha256:a099afb4d9a9c6bf9e5e93d59bc1aa866f860cc49e0492bfafa53bc834b220ce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 34.924800872802734,
-  "best_model_checkpoint": "/kaggle/working/output/checkpoint-6525",
-  "epoch": 5.0,
+  "best_metric": 34.841033935546875,
+  "best_model_checkpoint": "/kaggle/working/output/checkpoint-7830",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 6525,
+  "global_step": 7830,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -502,6 +502,105 @@
       "eval_samples_per_second": 26.47,
       "eval_steps_per_second": 3.327,
       "step": 6525
+    },
+    {
+      "epoch": 5.057471264367816,
+      "grad_norm": 2.3083884716033936,
+      "learning_rate": 4.684051724137931e-05,
+      "loss": 33.8987,
+      "step": 6600
+    },
+    {
+      "epoch": 5.134099616858237,
+      "grad_norm": 2.228327751159668,
+      "learning_rate": 4.67926245210728e-05,
+      "loss": 33.8189,
+      "step": 6700
+    },
+    {
+      "epoch": 5.210727969348659,
+      "grad_norm": 3.6814918518066406,
+      "learning_rate": 4.6744731800766284e-05,
+      "loss": 33.8364,
+      "step": 6800
+    },
+    {
+      "epoch": 5.287356321839081,
+      "grad_norm": 2.5758285522460938,
+      "learning_rate": 4.669683908045977e-05,
+      "loss": 33.7093,
+      "step": 6900
+    },
+    {
+      "epoch": 5.363984674329502,
+      "grad_norm": 4.175839900970459,
+      "learning_rate": 4.6648946360153265e-05,
+      "loss": 33.6689,
+      "step": 7000
+    },
+    {
+      "epoch": 5.440613026819923,
+      "grad_norm": 2.213092088699341,
+      "learning_rate": 4.6601053639846745e-05,
+      "loss": 33.7936,
+      "step": 7100
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 2.4982571601867676,
+      "learning_rate": 4.655316091954023e-05,
+      "loss": 33.3686,
+      "step": 7200
+    },
+    {
+      "epoch": 5.593869731800766,
+      "grad_norm": 3.635983943939209,
+      "learning_rate": 4.6505747126436784e-05,
+      "loss": 33.5493,
+      "step": 7300
+    },
+    {
+      "epoch": 5.670498084291188,
+      "grad_norm": 4.315894603729248,
+      "learning_rate": 4.645785440613027e-05,
+      "loss": 33.6607,
+      "step": 7400
+    },
+    {
+      "epoch": 5.747126436781609,
+      "grad_norm": 2.6151223182678223,
+      "learning_rate": 4.640996168582376e-05,
+      "loss": 34.7535,
+      "step": 7500
+    },
+    {
+      "epoch": 5.823754789272031,
+      "grad_norm": 4.03953218460083,
+      "learning_rate": 4.6362068965517244e-05,
+      "loss": 33.9865,
+      "step": 7600
+    },
+    {
+      "epoch": 5.900383141762452,
+      "grad_norm": 2.512362480163574,
+      "learning_rate": 4.6314176245210724e-05,
+      "loss": 33.0343,
+      "step": 7700
+    },
+    {
+      "epoch": 5.977011494252873,
+      "grad_norm": 4.745575428009033,
+      "learning_rate": 4.626628352490422e-05,
+      "loss": 33.4544,
+      "step": 7800
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 34.841033935546875,
+      "eval_runtime": 49.3059,
+      "eval_samples_per_second": 26.467,
+      "eval_steps_per_second": 3.326,
+      "step": 7830
     }
   ],
   "logging_steps": 100,
@@ -530,7 +629,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7036554515235840.0,
+  "total_flos": 8443865418283008.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null