Training in progress, step 37, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9015c86dc25befeb0d3169bebf1301e01f29c674a0a9e83bbb833c86915100c
+oid sha256:18b643a0d885230f5a0437db3e4af4a1fe36b5d89a67c8b170ba333a64fe01e4
 size 37352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93fafa34a5f4b89022303d36440045581e58ce710c360feae1b59fe992181252
+oid sha256:feafc958b07dacce078c9826ab8f00b78eb58f48b057a3a515086f080c74daf1
 size 83444

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c73512b05b9beb970d9c230af4efa7a8dc3b4fd36ad026ca0f590f2e8737d48
+oid sha256:b96f0eb56ba8557a197667600806dea2be8234032945e9d08e5e3794c926c3ee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0d2ea6335bd3947ae84603b4094a4b89eb75a80756a6b1fb0ef75533f6f325
+oid sha256:1525a0af52304123e8a1fffde73b195054e95c85af6a6d5d4de550411aeddf0e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd13ff2740c031b96a5874af3878e8fb3d0a65e4d673f4fc602556ae4260824
+oid sha256:45db4df4a0e8a74454a6fb2495e35a8da476b43a053eb44427c0697806b6d4b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f0ef04c1cec259f55fb71c771fbbae41c159be02436d43fb898a4a590cf404
+oid sha256:65e7f837d9c225387f6d912efdd7a06c07d64c89e7579546b8f97fcd4f7ba942
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec53e945c45054b00fddcb1b630559fc3ac4abaf959b53db326cce0461de3a8
+oid sha256:07dad002b9eddae7ca1e092b675b66e89a8b668e40c1ddc7dfb47cd4a5daaef6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.4584321975708,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.0725388601036268,
+  "epoch": 3.0673575129533677,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 37,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,90 @@
       "eval_samples_per_second": 380.993,
       "eval_steps_per_second": 51.109,
       "step": 25
+    },
+    {
+      "epoch": 2.155440414507772,
+      "grad_norm": 0.023453839123249054,
+      "learning_rate": 2.245515092739488e-05,
+      "loss": 12.3639,
+      "step": 26
+    },
+    {
+      "epoch": 2.238341968911917,
+      "grad_norm": 0.02777229994535446,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 12.6757,
+      "step": 27
+    },
+    {
+      "epoch": 2.321243523316062,
+      "grad_norm": 0.02316541038453579,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 12.2681,
+      "step": 28
+    },
+    {
+      "epoch": 2.4041450777202074,
+      "grad_norm": 0.02422947622835636,
+      "learning_rate": 1.2346426699819458e-05,
+      "loss": 12.4471,
+      "step": 29
+    },
+    {
+      "epoch": 2.4870466321243523,
+      "grad_norm": 0.02776755392551422,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 12.5286,
+      "step": 30
+    },
+    {
+      "epoch": 2.5699481865284977,
+      "grad_norm": 0.022363506257534027,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 12.452,
+      "step": 31
+    },
+    {
+      "epoch": 2.6528497409326426,
+      "grad_norm": 0.024167869240045547,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 12.3364,
+      "step": 32
+    },
+    {
+      "epoch": 2.7357512953367875,
+      "grad_norm": 0.029816903173923492,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 12.6708,
+      "step": 33
+    },
+    {
+      "epoch": 2.818652849740933,
+      "grad_norm": 0.022897807881236076,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 12.2847,
+      "step": 34
+    },
+    {
+      "epoch": 2.901554404145078,
+      "grad_norm": 0.022587254643440247,
+      "learning_rate": 8.035205700685167e-07,
+      "loss": 12.4786,
+      "step": 35
+    },
+    {
+      "epoch": 2.9844559585492227,
+      "grad_norm": 0.028138399124145508,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 12.6596,
+      "step": 36
+    },
+    {
+      "epoch": 3.0673575129533677,
+      "grad_norm": 0.04486376419663429,
+      "learning_rate": 0.0,
+      "loss": 24.0609,
+      "step": 37
     }
   ],
   "logging_steps": 1,
@@ -221,12 +305,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 421527552000.0,
+  "total_flos": 623860776960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null