Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d238086cc6122e00c4d18a8b193b02a3854186533dcd20143f61afc4b7567cd
+oid sha256:e32964f362d30a0a6a4704b1af2a5688af8a465dfe8494a6c3afab22c6b1dd44
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035afb65d8c4c653530eab72eb90902a9fa6bbb8343bb7ec0c79041dfa7de3a6
+oid sha256:c94e982eca0289d56b3761fa935bca5ab2036eb25f7662a636cf1378fac1e6bf
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0d3a45291a0dc77d430f021257e70e3a687a5c5bf48543bc1a94f23cf3d529
+oid sha256:8db1e2428f82460d3b721cf3d963b3a91f0b2118e39c1be11ced5dadb494343d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1b8d5c0a36c3e33eb80a28130ced20753960666c11a9d364c42a05c1f60501
+oid sha256:3c16e93a57ec407ef5820818dc09b38c026876f6fe4754a23f571241b2ef10bf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc834427a9918713d3cdb1af7e6881d67d9411e4ced7f80adea23b9217b1db3
+oid sha256:a2a42541606e3e23c69a211394dcc2288ce2a7f1aa7ddb40d52a11e0353457ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f218162af756a989d31d0c4ddcd489b77f95d7167ad15214541b49fafd0f3e2c
+oid sha256:263a31b7bc3c2b2072b13a030e1ea7bef918641c552e78e097be7abe47f5cf0b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.001101016998291,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2089864158829676,
+  "best_metric": 0.9690943360328674,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4179728317659352,
   "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": 42.962,
       "eval_steps_per_second": 11.17,
       "step": 25
+    },
+    {
+      "epoch": 0.2173458725182863,
+      "grad_norm": 0.4371124804019928,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8685,
+      "step": 26
+    },
+    {
+      "epoch": 0.22570532915360503,
+      "grad_norm": 0.39926087856292725,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.959,
+      "step": 27
+    },
+    {
+      "epoch": 0.23406478578892373,
+      "grad_norm": 0.42637521028518677,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0602,
+      "step": 28
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.40809735655784607,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0049,
+      "step": 29
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.4572559595108032,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0438,
+      "step": 30
+    },
+    {
+      "epoch": 0.25914315569487983,
+      "grad_norm": 0.39180684089660645,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.97,
+      "step": 31
+    },
+    {
+      "epoch": 0.26750261233019856,
+      "grad_norm": 0.4096227288246155,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0363,
+      "step": 32
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.4008356034755707,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0532,
+      "step": 33
+    },
+    {
+      "epoch": 0.28422152560083597,
+      "grad_norm": 0.4251631796360016,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0442,
+      "step": 34
+    },
+    {
+      "epoch": 0.29258098223615464,
+      "grad_norm": 0.4049515128135681,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0944,
+      "step": 35
+    },
+    {
+      "epoch": 0.30094043887147337,
+      "grad_norm": 0.47100144624710083,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0576,
+      "step": 36
+    },
+    {
+      "epoch": 0.30929989550679204,
+      "grad_norm": 0.4920854866504669,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0766,
+      "step": 37
+    },
+    {
+      "epoch": 0.3176593521421108,
+      "grad_norm": 0.45009514689445496,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8845,
+      "step": 38
+    },
+    {
+      "epoch": 0.32601880877742945,
+      "grad_norm": 0.4449792802333832,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9975,
+      "step": 39
+    },
+    {
+      "epoch": 0.3343782654127482,
+      "grad_norm": 0.4090271294116974,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9589,
+      "step": 40
+    },
+    {
+      "epoch": 0.34273772204806685,
+      "grad_norm": 0.3993270993232727,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9349,
+      "step": 41
+    },
+    {
+      "epoch": 0.3510971786833856,
+      "grad_norm": 0.3873380124568939,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0709,
+      "step": 42
+    },
+    {
+      "epoch": 0.3594566353187043,
+      "grad_norm": 0.37261834740638733,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.0381,
+      "step": 43
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.3891456127166748,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0721,
+      "step": 44
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.3773375153541565,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9904,
+      "step": 45
+    },
+    {
+      "epoch": 0.3845350052246604,
+      "grad_norm": 0.42510074377059937,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0608,
+      "step": 46
+    },
+    {
+      "epoch": 0.3928944618599791,
+      "grad_norm": 0.4486747086048126,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0842,
+      "step": 47
+    },
+    {
+      "epoch": 0.4012539184952978,
+      "grad_norm": 0.4293101727962494,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1138,
+      "step": 48
+    },
+    {
+      "epoch": 0.4096133751306165,
+      "grad_norm": 0.4755518138408661,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0434,
+      "step": 49
+    },
+    {
+      "epoch": 0.4179728317659352,
+      "grad_norm": 0.4889579713344574,
+      "learning_rate": 1e-05,
+      "loss": 1.1573,
+      "step": 50
+    },
+    {
+      "epoch": 0.4179728317659352,
+      "eval_loss": 0.9690943360328674,
+      "eval_runtime": 1.1476,
+      "eval_samples_per_second": 43.568,
+      "eval_steps_per_second": 11.328,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null