Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c59218aeed30c8b4e4d689a63794cee1afc92cbe005871cb267aa12eddebe28
+oid sha256:f64f44255fc6a71075712992b10e7db97e69c91efa5e69776ec2fc144a4efb3b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a0f559bdd44b5b313e2769f89c5a87aeb83788402322c137889ceed21eef3f
+oid sha256:c4901ff228d37f80b8593785a4d03ec9a436ef383d867132df3f3fed6f5f8db7
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7c72f98dacab526d7f08eec0014de02c536c465ede32e975e11056d306de6b
+oid sha256:2b40f8c21535d5cb3040ebd6098de18bc4b54d3919e39854677564dd2248fca8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b149256f5213147bb7dda2c43f9b7eba4882d860494af34e39bbc6c6d7e0e1c0
+oid sha256:0a99fbc57599ab28bd8c12c1c1421120e46a75f8dbf99fa457773e219d0648ec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e31681cbdbe7be2a44f51e44e9fc4bea2061ee88a5c23a0ca17909c99e6639
+oid sha256:c5c819c7818a631c0cb290b3977e95c7f54598a017022454f25e1aeda1c08663
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483761894f386ce5c613b15225f8f41e70cee47fb6633ab8084f8e3faa2fffff
+oid sha256:eedcb0330f97ca4e8d8dc31801d05424a6942b71102d32b41ed9c1b09503809c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52d696b576c80447b09be7d8794036033efac5da11af94320214f843d978cbe
+oid sha256:07c71024bc4e99ca36ceb2f728e261e6c0a3853b01e7c038fbdeb0dde69b327f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1290745735168457,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.4188790560471976,
+  "epoch": 3.1091445427728615,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,55 @@
       "eval_samples_per_second": 11.465,
       "eval_steps_per_second": 2.981,
       "step": 25
+    },
+    {
+      "epoch": 2.5132743362831858,
+      "grad_norm": 0.819108784198761,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.9056,
+      "step": 26
+    },
+    {
+      "epoch": 2.607669616519174,
+      "grad_norm": 0.766586184501648,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8938,
+      "step": 27
+    },
+    {
+      "epoch": 2.702064896755162,
+      "grad_norm": 0.7301772832870483,
+      "learning_rate": 1.389045440608296e-05,
+      "loss": 0.6849,
+      "step": 28
+    },
+    {
+      "epoch": 2.7964601769911503,
+      "grad_norm": 0.8863487839698792,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 1.1958,
+      "step": 29
+    },
+    {
+      "epoch": 2.8908554572271385,
+      "grad_norm": 0.8773151636123657,
+      "learning_rate": 1.0983357966978745e-05,
+      "loss": 0.8598,
+      "step": 30
+    },
+    {
+      "epoch": 3.0147492625368733,
+      "grad_norm": 1.5916945934295654,
+      "learning_rate": 1.0246514708427702e-05,
+      "loss": 1.5241,
+      "step": 31
+    },
+    {
+      "epoch": 3.1091445427728615,
+      "grad_norm": 0.6731727123260498,
+      "learning_rate": 1e-05,
+      "loss": 0.8907,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -221,12 +270,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 3.819573515082793e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null