Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780ee40d53334ce492d5f31b490f169c22e541e2755ce8950e484a10b5558706
+oid sha256:84601eb8725e9cdad2f19fcdcbf1a430e41f8eaa2ff6c6194cb634db60c2b88f
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7568e9e2b53495070a10c4459eaf0c88724249f91175a7c05362dbc25103a119
+oid sha256:0acb2f67fa336c04249919be0cd7d5376ed458061caa3639536bbf675cb69257
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e5a0269fb77f18e3aceab5fac1fa5bf76f8e9a0652931915ce1c218d4968e0
+oid sha256:77366c5b0912fa56458010da901358791aaa2796f2cbae54ef844e1f493656b8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f67f77e67876d6cfa255664a53d8a9eba8b45a78eac1576db27506d43c4d900
+oid sha256:80547ef4729b9177414a092feb2ba2e3e71ed2b079a7207fcbbaab3bc6d28d28
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3fb96a29081398a6f085edcf4dbc751aa2abca1f4f1b427f38e11c24020466
+oid sha256:2e7c9063e5732fe73f6523dcfae64d929c2bbcb60b38bf913a3f84466abca2f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a3cf8f6339443cfe88b73e1e6572153b3e75d9ffbd8fa046c4bfe83bb245e0
+oid sha256:88ac0bf3af6e2d26476efc4ecf5b68aa017de1b5b67d2d99a0a855ac60342602
 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": 2.9548091888427734,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.018481726193226446,
+  "best_metric": 2.8744540214538574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03696345238645289,
   "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": 9.407,
       "eval_steps_per_second": 1.177,
       "step": 25
+    },
+    {
+      "epoch": 0.019220995240955507,
+      "grad_norm": 1.4390382766723633,
+      "learning_rate": 5e-05,
+      "loss": 2.6398,
+      "step": 26
+    },
+    {
+      "epoch": 0.019960264288684564,
+      "grad_norm": 1.285017490386963,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.6834,
+      "step": 27
+    },
+    {
+      "epoch": 0.020699533336413622,
+      "grad_norm": 0.7559266686439514,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.7456,
+      "step": 28
+    },
+    {
+      "epoch": 0.02143880238414268,
+      "grad_norm": 0.438568651676178,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.7858,
+      "step": 29
+    },
+    {
+      "epoch": 0.022178071431871737,
+      "grad_norm": 0.36864879727363586,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8327,
+      "step": 30
+    },
+    {
+      "epoch": 0.022917340479600794,
+      "grad_norm": 1.0010043382644653,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.8275,
+      "step": 31
+    },
+    {
+      "epoch": 0.023656609527329852,
+      "grad_norm": 1.105016827583313,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.8782,
+      "step": 32
+    },
+    {
+      "epoch": 0.02439587857505891,
+      "grad_norm": 0.4782523512840271,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.9056,
+      "step": 33
+    },
+    {
+      "epoch": 0.025135147622787967,
+      "grad_norm": 0.6142726540565491,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.0591,
+      "step": 34
+    },
+    {
+      "epoch": 0.025874416670517025,
+      "grad_norm": 0.6701408624649048,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.0697,
+      "step": 35
+    },
+    {
+      "epoch": 0.026613685718246086,
+      "grad_norm": 0.6728911399841309,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.0663,
+      "step": 36
+    },
+    {
+      "epoch": 0.027352954765975143,
+      "grad_norm": 1.5853469371795654,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.1271,
+      "step": 37
+    },
+    {
+      "epoch": 0.0280922238137042,
+      "grad_norm": 0.5142918825149536,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.5163,
+      "step": 38
+    },
+    {
+      "epoch": 0.02883149286143326,
+      "grad_norm": 0.5276281237602234,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.6449,
+      "step": 39
+    },
+    {
+      "epoch": 0.029570761909162316,
+      "grad_norm": 0.5071715712547302,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.6503,
+      "step": 40
+    },
+    {
+      "epoch": 0.030310030956891373,
+      "grad_norm": 0.4902350604534149,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.7115,
+      "step": 41
+    },
+    {
+      "epoch": 0.03104930000462043,
+      "grad_norm": 0.5433118939399719,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.7676,
+      "step": 42
+    },
+    {
+      "epoch": 0.03178856905234949,
+      "grad_norm": 0.44246047735214233,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.8322,
+      "step": 43
+    },
+    {
+      "epoch": 0.032527838100078546,
+      "grad_norm": 0.5774577856063843,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8249,
+      "step": 44
+    },
+    {
+      "epoch": 0.033267107147807604,
+      "grad_norm": 0.3766028583049774,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.9393,
+      "step": 45
+    },
+    {
+      "epoch": 0.03400637619553666,
+      "grad_norm": 0.5460787415504456,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.0283,
+      "step": 46
+    },
+    {
+      "epoch": 0.03474564524326572,
+      "grad_norm": 0.6633034944534302,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.9091,
+      "step": 47
+    },
+    {
+      "epoch": 0.035484914290994776,
+      "grad_norm": 0.7276972532272339,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.0902,
+      "step": 48
+    },
+    {
+      "epoch": 0.036224183338723834,
+      "grad_norm": 0.775564432144165,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1153,
+      "step": 49
+    },
+    {
+      "epoch": 0.03696345238645289,
+      "grad_norm": 2.0693697929382324,
+      "learning_rate": 0.0,
+      "loss": 3.2925,
+      "step": 50
+    },
+    {
+      "epoch": 0.03696345238645289,
+      "eval_loss": 2.8744540214538574,
+      "eval_runtime": 968.9207,
+      "eval_samples_per_second": 9.405,
+      "eval_steps_per_second": 1.177,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null