Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3e6fd00c8a6edf32244c60fbab55b1905045e8cfca52eacc1d00a5ed94b653
+oid sha256:58f8179ef7267f2a8a03b514b4f65d883c7710bb53b798709e9cc1a15eab89e7
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f84b9b974c9f4ae3556b9c742aca5950b3b7cdd74c780a66b4ccbcf679517ff
+oid sha256:f3b739486dd67668d4ec06b202d37d250dec6627a2be0a7d8622b2f133039b6a
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656cf9adc1148971a1bb484c810b220161fa2f640c22a0cecef8db678d87dcce
+oid sha256:18449718104b618e79ca842aab308da0d1114677f57be00c8e1aacd557e1b06b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e22502c65b64ca0b58cf1a2197838a24ff5e1a35c0b17ecc01a4313b65e468
+oid sha256:1fc9d534bafeaa873d59b385fbf9bf46ea1bb73bdb857445cccaddbd24128764
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855655eaa1f69d3c5954146587c9875625878969a5eb91788f4b0cd2835a220a
+oid sha256:5ff545e85dd6ead9f30e6c443db4364f34be6becb3f61bc26ca4bc9a89e48b84
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483d7d7c031662ba6eee45a8c1647527c5cb6a1c65fcd34463f311160a1d6dde
+oid sha256:87bf05c1f661bc9e58186ff51ea5da4e2f920141ae4ef825e8d70746c0d9ed32
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53322a9e0770f1aa889f3dc8eda417cbde627f634c75503b1e43849ff496ab
+oid sha256:d50872ebe2ae52bfb0e335aaa2e28a3dac724479a77b01ce7ef36e8156017c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.038246795535087585,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.9607843137254903,
+  "epoch": 3.0588235294117645,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,104 @@
       "eval_samples_per_second": 27.331,
       "eval_steps_per_second": 7.106,
       "step": 25
+    },
+    {
+      "epoch": 2.0392156862745097,
+      "grad_norm": 3.510915994644165,
+      "learning_rate": 3.474083148320469e-05,
+      "loss": 0.4248,
+      "step": 26
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 8.030313491821289,
+      "learning_rate": 3.1406172239924584e-05,
+      "loss": 0.8069,
+      "step": 27
+    },
+    {
+      "epoch": 2.196078431372549,
+      "grad_norm": 26.57486915588379,
+      "learning_rate": 2.8241507066307104e-05,
+      "loss": 1.1415,
+      "step": 28
+    },
+    {
+      "epoch": 2.2745098039215685,
+      "grad_norm": 6.342585563659668,
+      "learning_rate": 2.5269637447446348e-05,
+      "loss": 0.0675,
+      "step": 29
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 20.42534065246582,
+      "learning_rate": 2.2511975772046403e-05,
+      "loss": 1.1795,
+      "step": 30
+    },
+    {
+      "epoch": 2.431372549019608,
+      "grad_norm": 71.26493835449219,
+      "learning_rate": 1.9988391055670233e-05,
+      "loss": 1.4359,
+      "step": 31
+    },
+    {
+      "epoch": 2.5098039215686274,
+      "grad_norm": 4.1655449867248535,
+      "learning_rate": 1.771706578402711e-05,
+      "loss": 0.0568,
+      "step": 32
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 12.102375030517578,
+      "learning_rate": 1.5714364907746536e-05,
+      "loss": 0.9678,
+      "step": 33
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 25.678956985473633,
+      "learning_rate": 1.3994717932533891e-05,
+      "loss": 1.2355,
+      "step": 34
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 1.5909215211868286,
+      "learning_rate": 1.257051495425121e-05,
+      "loss": 0.0221,
+      "step": 35
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 33.322696685791016,
+      "learning_rate": 1.1452017387992552e-05,
+      "loss": 1.1316,
+      "step": 36
+    },
+    {
+      "epoch": 2.9019607843137254,
+      "grad_norm": 23.584259033203125,
+      "learning_rate": 1.064728403435312e-05,
+      "loss": 0.9945,
+      "step": 37
+    },
+    {
+      "epoch": 2.980392156862745,
+      "grad_norm": 6.629971981048584,
+      "learning_rate": 1.0162113015586309e-05,
+      "loss": 0.3805,
+      "step": 38
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 8.110614776611328,
+      "learning_rate": 1e-05,
+      "loss": 0.5328,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -221,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.631214808694784e+17,
+  "total_flos": 4.104695101563863e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null