Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c70fa5bd3019c2f21db8122c87d12cd6330e95c21988a27922a18a0127a7c6
+oid sha256:dce8f8856c2efd7382f9b9e2a4fe12b00b61d44949107efc024e135276f2fdc8
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc262d2b0ab2be611311b2cb7b37af4b02a5efc24667138b28e6ae4b9c69e49
+oid sha256:bfe16b2a0f33c549a3839a37a89e9b93abb4765a7bb87dd5f882f4dfdeda22d5
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5097a2fa189f72e67e54faa03af535c7ca15c8c279f535ec2684a8750f8ba2ff
+oid sha256:f718e7dd3b9cb87c504ffc48bd13d55cc2f00494fff18a58a23c22fe7ad76678
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb27da341d5af21d403764d0c476acecc453d3e2211352904e128d8a22abdd54
+oid sha256:0b03d3d28e89d9fd412a9ce650e3cd74ba4b669fb777294ec0d1b0d38b84c701
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.997999636297509,
+  "epoch": 7.997999636297509,
   "eval_steps": 50,
-  "global_step": 2401,
+  "global_step": 2744,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,96 @@
       "eval_samples_per_second": 41.372,
       "eval_steps_per_second": 20.686,
       "step": 2400
+    },
+    {
+      "epoch": 7.14257137661393,
+      "grad_norm": 49.362857818603516,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.8429,
+      "step": 2450
+    },
+    {
+      "epoch": 7.14257137661393,
+      "eval_loss": 0.8078887462615967,
+      "eval_runtime": 116.7726,
+      "eval_samples_per_second": 41.328,
+      "eval_steps_per_second": 20.664,
+      "step": 2450
+    },
+    {
+      "epoch": 7.288052373158756,
+      "grad_norm": 73.06404113769531,
+      "learning_rate": 6.355685131195336e-05,
+      "loss": 0.8374,
+      "step": 2500
+    },
+    {
+      "epoch": 7.288052373158756,
+      "eval_loss": 0.8106158375740051,
+      "eval_runtime": 116.3346,
+      "eval_samples_per_second": 41.484,
+      "eval_steps_per_second": 20.742,
+      "step": 2500
+    },
+    {
+      "epoch": 7.433533369703582,
+      "grad_norm": 72.56304931640625,
+      "learning_rate": 6.282798833819243e-05,
+      "loss": 0.8371,
+      "step": 2550
+    },
+    {
+      "epoch": 7.433533369703582,
+      "eval_loss": 0.8068947792053223,
+      "eval_runtime": 116.5087,
+      "eval_samples_per_second": 41.422,
+      "eval_steps_per_second": 20.711,
+      "step": 2550
+    },
+    {
+      "epoch": 7.579014366248408,
+      "grad_norm": 62.97400665283203,
+      "learning_rate": 6.209912536443149e-05,
+      "loss": 0.8323,
+      "step": 2600
+    },
+    {
+      "epoch": 7.579014366248408,
+      "eval_loss": 0.804251492023468,
+      "eval_runtime": 116.5526,
+      "eval_samples_per_second": 41.406,
+      "eval_steps_per_second": 20.703,
+      "step": 2600
+    },
+    {
+      "epoch": 7.724495362793235,
+      "grad_norm": 46.578704833984375,
+      "learning_rate": 6.137026239067056e-05,
+      "loss": 0.8381,
+      "step": 2650
+    },
+    {
+      "epoch": 7.724495362793235,
+      "eval_loss": 0.7970871925354004,
+      "eval_runtime": 116.4414,
+      "eval_samples_per_second": 41.446,
+      "eval_steps_per_second": 20.723,
+      "step": 2650
+    },
+    {
+      "epoch": 7.869976359338062,
+      "grad_norm": 63.2580680847168,
+      "learning_rate": 6.0641399416909626e-05,
+      "loss": 0.833,
+      "step": 2700
+    },
+    {
+      "epoch": 7.869976359338062,
+      "eval_loss": 0.7932024002075195,
+      "eval_runtime": 116.5379,
+      "eval_samples_per_second": 41.411,
+      "eval_steps_per_second": 20.706,
+      "step": 2700
     }
   ],
   "logging_steps": 50,
@@ -746,7 +836,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.253897047531848e+17,
+  "total_flos": 7.148087838884495e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null