Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c768093d7e707272b88b8681161101482d91ff27d34707c835688cfb66a484
+oid sha256:10fe4c9eaf89c279692494435e8e59f43d08e0c5e81b4d536aad476957a85000
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c83365661ca55181717555fd4f031c94bd9d3c0846378f0e848128d7cc2cd0b
+oid sha256:af6b942bc263b96b0724fcb508944342657646af2a84cd6c9f0abc1a1f1af403
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9404daff786212647adae37fe2da75d552625d004cba5f320a9ff699d3d0fb10
+oid sha256:a6ab8b33d605a9b3ebe223321ce2c3b20eaa96cd2dc4c3b5bb9d7a243e720b3a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63012b6efda9d84cc4848e8b5ee45ce563a6507cd33a7c7a33274f0f09037e75
+oid sha256:b87d0a24af1e9a698bde6cf13c57192ac6eb5925d9159cf7e4649fe2fec58818
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eeb243c384ce8fc44c40f20541b6588764eeedc39cf6878e3a85acf147afd44
+oid sha256:c6c97e5546be3c13687d0b9eb3d23ee782149c21a3a59d0b5bb6f7eee9ab229e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e2056053203985537510bbda269726e6ee1a0a97ba52768c8acfddc716b54a
+oid sha256:dc67fdb3767482a06aa15974ebcca872322c862d5d888066968bfe7cf04d5b41
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 7.125263214111328,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06443298969072164,
+  "best_metric": 7.067266941070557,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12886597938144329,
   "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": 100.182,
       "eval_steps_per_second": 12.532,
       "step": 25
+    },
+    {
+      "epoch": 0.06701030927835051,
+      "grad_norm": 2.849268674850464,
+      "learning_rate": 5e-05,
+      "loss": 7.2586,
+      "step": 26
+    },
+    {
+      "epoch": 0.06958762886597938,
+      "grad_norm": 1.6071581840515137,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 7.837,
+      "step": 27
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 1.3252266645431519,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.5216,
+      "step": 28
+    },
+    {
+      "epoch": 0.07474226804123711,
+      "grad_norm": 1.1092205047607422,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 7.42,
+      "step": 29
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.9314132928848267,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 7.3253,
+      "step": 30
+    },
+    {
+      "epoch": 0.07989690721649484,
+      "grad_norm": 0.9957264065742493,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 7.4278,
+      "step": 31
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 1.0452556610107422,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.961,
+      "step": 32
+    },
+    {
+      "epoch": 0.08505154639175258,
+      "grad_norm": 0.9974004626274109,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 7.1028,
+      "step": 33
+    },
+    {
+      "epoch": 0.08762886597938144,
+      "grad_norm": 0.866974949836731,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.855,
+      "step": 34
+    },
+    {
+      "epoch": 0.09020618556701031,
+      "grad_norm": 0.9052703976631165,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.8511,
+      "step": 35
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "grad_norm": 0.9637014269828796,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.7397,
+      "step": 36
+    },
+    {
+      "epoch": 0.09536082474226804,
+      "grad_norm": 1.1197189092636108,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.6541,
+      "step": 37
+    },
+    {
+      "epoch": 0.0979381443298969,
+      "grad_norm": 1.420501708984375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.7482,
+      "step": 38
+    },
+    {
+      "epoch": 0.10051546391752578,
+      "grad_norm": 1.498699426651001,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 7.6799,
+      "step": 39
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 1.1142817735671997,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.5234,
+      "step": 40
+    },
+    {
+      "epoch": 0.1056701030927835,
+      "grad_norm": 1.0226730108261108,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 7.4547,
+      "step": 41
+    },
+    {
+      "epoch": 0.10824742268041238,
+      "grad_norm": 0.8474833965301514,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.4219,
+      "step": 42
+    },
+    {
+      "epoch": 0.11082474226804123,
+      "grad_norm": 0.9374727010726929,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 7.2288,
+      "step": 43
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 0.9378708004951477,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.1749,
+      "step": 44
+    },
+    {
+      "epoch": 0.11597938144329897,
+      "grad_norm": 0.847159743309021,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 7.0036,
+      "step": 45
+    },
+    {
+      "epoch": 0.11855670103092783,
+      "grad_norm": 0.8835762143135071,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.9541,
+      "step": 46
+    },
+    {
+      "epoch": 0.1211340206185567,
+      "grad_norm": 0.8930884003639221,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.8733,
+      "step": 47
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.8807015419006348,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.6641,
+      "step": 48
+    },
+    {
+      "epoch": 0.12628865979381443,
+      "grad_norm": 0.9850261807441711,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.8159,
+      "step": 49
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 1.192939281463623,
+      "learning_rate": 0.0,
+      "loss": 6.6461,
+      "step": 50
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 7.067266941070557,
+      "eval_runtime": 25.9801,
+      "eval_samples_per_second": 100.616,
+      "eval_steps_per_second": 12.587,
+      "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": 119559610171392.0,
+  "total_flos": 239916767772672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null