Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2170f363af75bee423329c0e7195eebd93c29a91127f9ed7355476823694d12a
+oid sha256:efb02b75b47c85ad0131de305fe0696b3258a69ce235a03cda5385ed088789bf
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5cd25137bbcff7ad6794f9961c6c616804069147ffc3587d6ee599a3f46b83
+oid sha256:39a9b3a39d204a0389ebf8339e62f265bc7b8fe372d31f11b523bec781ce71d9
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f4b12d30ea17d7246e91cf6c0974c32199b5ee598c5161d160f3653042daa8
+oid sha256:54a03131e9a31ec32228d267d0c159f95fb78bfd9d01618428f4dd0bfe819456
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a49108293edbb6877a3e9ba0d52e802c533bf4a33edff9df48f4e84b4fa057
+oid sha256:ca2ad0660f4430a149f84300447ae0a59e68e8b51799a2e3848afe158aff8281
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.079472541809082,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03266372693124286,
+  "best_metric": 11.069597244262695,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06532745386248572,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 278.988,
       "eval_steps_per_second": 69.801,
       "step": 25
+    },
+    {
+      "epoch": 0.03397027600849257,
+      "grad_norm": 3.7262842655181885,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 177.2893,
+      "step": 26
+    },
+    {
+      "epoch": 0.035276825085742286,
+      "grad_norm": 3.6478946208953857,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 177.243,
+      "step": 27
+    },
+    {
+      "epoch": 0.036583374162992,
+      "grad_norm": 3.6439425945281982,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 177.2659,
+      "step": 28
+    },
+    {
+      "epoch": 0.037889923240241714,
+      "grad_norm": 3.4257993698120117,
+      "learning_rate": 1.45e-05,
+      "loss": 177.2895,
+      "step": 29
+    },
+    {
+      "epoch": 0.039196472317491425,
+      "grad_norm": 3.6870901584625244,
+      "learning_rate": 1.5e-05,
+      "loss": 177.2226,
+      "step": 30
+    },
+    {
+      "epoch": 0.04050302139474114,
+      "grad_norm": 3.4951345920562744,
+      "learning_rate": 1.55e-05,
+      "loss": 177.2335,
+      "step": 31
+    },
+    {
+      "epoch": 0.04180957047199085,
+      "grad_norm": 3.806819200515747,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 177.2805,
+      "step": 32
+    },
+    {
+      "epoch": 0.04311611954924057,
+      "grad_norm": 3.3956995010375977,
+      "learning_rate": 1.65e-05,
+      "loss": 177.2527,
+      "step": 33
+    },
+    {
+      "epoch": 0.04442266862649028,
+      "grad_norm": 3.5464022159576416,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 177.2337,
+      "step": 34
+    },
+    {
+      "epoch": 0.04572921770374,
+      "grad_norm": 3.3746349811553955,
+      "learning_rate": 1.75e-05,
+      "loss": 177.2345,
+      "step": 35
+    },
+    {
+      "epoch": 0.04703576678098971,
+      "grad_norm": 3.7294857501983643,
+      "learning_rate": 1.8e-05,
+      "loss": 177.1912,
+      "step": 36
+    },
+    {
+      "epoch": 0.04834231585823943,
+      "grad_norm": 3.639246940612793,
+      "learning_rate": 1.85e-05,
+      "loss": 177.2383,
+      "step": 37
+    },
+    {
+      "epoch": 0.04964886493548914,
+      "grad_norm": 3.5819694995880127,
+      "learning_rate": 1.9e-05,
+      "loss": 177.1814,
+      "step": 38
+    },
+    {
+      "epoch": 0.050955414012738856,
+      "grad_norm": 3.935349941253662,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 177.1835,
+      "step": 39
+    },
+    {
+      "epoch": 0.05226196308998857,
+      "grad_norm": 3.4866220951080322,
+      "learning_rate": 2e-05,
+      "loss": 177.2147,
+      "step": 40
+    },
+    {
+      "epoch": 0.053568512167238284,
+      "grad_norm": 3.7808289527893066,
+      "learning_rate": 2.05e-05,
+      "loss": 177.1828,
+      "step": 41
+    },
+    {
+      "epoch": 0.054875061244487995,
+      "grad_norm": 3.6725897789001465,
+      "learning_rate": 2.1e-05,
+      "loss": 177.2215,
+      "step": 42
+    },
+    {
+      "epoch": 0.05618161032173771,
+      "grad_norm": 3.587181568145752,
+      "learning_rate": 2.15e-05,
+      "loss": 177.1966,
+      "step": 43
+    },
+    {
+      "epoch": 0.05748815939898742,
+      "grad_norm": 3.692125082015991,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 177.1116,
+      "step": 44
+    },
+    {
+      "epoch": 0.05879470847623714,
+      "grad_norm": 3.829174757003784,
+      "learning_rate": 2.25e-05,
+      "loss": 177.1447,
+      "step": 45
+    },
+    {
+      "epoch": 0.06010125755348685,
+      "grad_norm": 3.735208034515381,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 177.1658,
+      "step": 46
+    },
+    {
+      "epoch": 0.06140780663073657,
+      "grad_norm": 3.433053731918335,
+      "learning_rate": 2.35e-05,
+      "loss": 177.1407,
+      "step": 47
+    },
+    {
+      "epoch": 0.06271435570798628,
+      "grad_norm": 3.8297133445739746,
+      "learning_rate": 2.4e-05,
+      "loss": 177.0864,
+      "step": 48
+    },
+    {
+      "epoch": 0.06402090478523599,
+      "grad_norm": 3.788440465927124,
+      "learning_rate": 2.45e-05,
+      "loss": 177.0926,
+      "step": 49
+    },
+    {
+      "epoch": 0.06532745386248572,
+      "grad_norm": 3.6808505058288574,
+      "learning_rate": 2.5e-05,
+      "loss": 177.1607,
+      "step": 50
+    },
+    {
+      "epoch": 0.06532745386248572,
+      "eval_loss": 11.069597244262695,
+      "eval_runtime": 9.1005,
+      "eval_samples_per_second": 283.28,
+      "eval_steps_per_second": 70.875,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1654652928000.0,
+  "total_flos": 3309305856000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null