Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5784cf0ea9815a03a806567b759299791c41b08d694fb9c7383f242a74b32610
+oid sha256:0669de46788b385d1864d042e3012a50eaabc302959603caa7a4a8b508fed047
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9a0344b87b16aeda1b6161d13facd80eb51979144fe2640b7acb1ec9a9e18c
+oid sha256:7562f117f208e3e39c614f3fc7ef59117312c519779862e3c4127c737276a251
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0b0741d6e7d7e6c3afcdaa2b6f9df57365ac351202f49d2b50178fe436e192
+oid sha256:56b0b736ba7e794c6825c083ee09502612769b2781725f4f635dfce7d52cb0f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7989693880081177,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.021197668256491786,
+  "best_metric": 0.5977821946144104,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04239533651298357,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 6.909,
       "eval_steps_per_second": 1.736,
       "step": 10
+    },
+    {
+      "epoch": 0.025437201907790145,
+      "grad_norm": 1.0461260080337524,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.9535,
+      "step": 12
+    },
+    {
+      "epoch": 0.03179650238473768,
+      "grad_norm": 0.7129300832748413,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.645,
+      "step": 15
+    },
+    {
+      "epoch": 0.03179650238473768,
+      "eval_loss": 0.6562170386314392,
+      "eval_runtime": 57.0299,
+      "eval_samples_per_second": 6.979,
+      "eval_steps_per_second": 1.753,
+      "step": 15
+    },
+    {
+      "epoch": 0.03815580286168521,
+      "grad_norm": 0.5910429954528809,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.3756,
+      "step": 18
+    },
+    {
+      "epoch": 0.04239533651298357,
+      "eval_loss": 0.5977821946144104,
+      "eval_runtime": 57.8021,
+      "eval_samples_per_second": 6.886,
+      "eval_steps_per_second": 1.73,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.306929288708096e+16,
+  "total_flos": 2.613858577416192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null