Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f93635858b3aa73868419876d606f7076aa593d9fbd3d570d2ea20616e06c4
+oid sha256:0b2b11a7902f4a6272acab614d3288e1cbea941ab4e9a42722cabd9f2b83e83c
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a3bcf065ace72e8909f857c5872e03400f951b93975188bc9f584203658aa9
+oid sha256:416bafe5b22e5f7ace80318ea2d1bc7180d3a64e1622164f5d820f128b0e0f81
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8980714a167437fc514efaf7b81039f9e904a2287a3dd851be639c06eb7dc062
+oid sha256:60e89622421ce2e2d153f71835fc528095bd9abe138034db31849fa6ee5972fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02631578947368421,
+  "epoch": 0.05263157894736842,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 211.427,
       "eval_steps_per_second": 105.714,
       "step": 15
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": 1122.0399169921875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 33.7543,
+      "step": 18
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": 8.328618049621582,
+      "eval_runtime": 1.1598,
+      "eval_samples_per_second": 206.938,
+      "eval_steps_per_second": 103.469,
+      "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 1370.0748291015625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 36.3826,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 1278.0841064453125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 34.4785,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": 8.307162284851074,
+      "eval_runtime": 1.1606,
+      "eval_samples_per_second": 206.792,
+      "eval_steps_per_second": 103.396,
+      "step": 25
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 1448.9915771484375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 34.2346,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 1308.057373046875,
+      "learning_rate": 0.0,
+      "loss": 30.9553,
+      "step": 30
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 8.286457061767578,
+      "eval_runtime": 1.1563,
+      "eval_samples_per_second": 207.558,
+      "eval_steps_per_second": 103.779,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 34631999029248.0,
+  "total_flos": 70939739947008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null