Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6facacf42ac7da5d289b076d7fff52d5931c4301b10a47e0ce67d31cfd52f463
+oid sha256:3a429bfc9712d372174478a0a1ceda8c4fb0605aaf0b6db44c0abe5c439cb399
 size 792912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb11e627e7d90a1f3e4a7e785196799e3fd06124e84fb349e1e11a53396fff5
+oid sha256:e93ae44a07d56b195542d4f6a8116ccf5339682e545352af1d95c1de8d949cd2
 size 807226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1ac4b7c8567fc2df96de548466abee568f08bf60059c07f33c87cc73b9aac2
+oid sha256:6443d93e1b3505255d44b3742cedcdaaf5b683dcf24f578d47dbf5f8bb42b08a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d71d2520220b24b14e74f15b8fc66bb3fd91884b9f80b2d1815e9fc2c23c
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38095238095238093,
+  "epoch": 0.7619047619047619,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,87 @@
       "eval_samples_per_second": 230.251,
       "eval_steps_per_second": 62.796,
       "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2037.5367431640625,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 13.7064,
+      "step": 21
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 1787.888671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 13.8959,
+      "step": 24
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_loss": 6.688287734985352,
+      "eval_runtime": 0.0989,
+      "eval_samples_per_second": 222.419,
+      "eval_steps_per_second": 60.66,
+      "step": 25
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 2035.425537109375,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 13.6203,
+      "step": 27
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2253.046875,
+      "learning_rate": 0.0001,
+      "loss": 13.3387,
+      "step": 30
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "eval_loss": 6.705076217651367,
+      "eval_runtime": 0.1247,
+      "eval_samples_per_second": 176.415,
+      "eval_steps_per_second": 48.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 1498.140380859375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 12.9927,
+      "step": 33
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 6.740316390991211,
+      "eval_runtime": 0.0977,
+      "eval_samples_per_second": 225.14,
+      "eval_steps_per_second": 61.402,
+      "step": 35
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 1960.5146484375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 13.6963,
+      "step": 36
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 1050.917724609375,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 13.3819,
+      "step": 39
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "eval_loss": 6.635408401489258,
+      "eval_runtime": 0.0974,
+      "eval_samples_per_second": 225.782,
+      "eval_steps_per_second": 61.577,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -103,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7692689080320.0,
+  "total_flos": 15385378160640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null