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:ad1d11abe82506d5da5ee1fef1cc562d194a70a7ac72e4fc9ce9d258e1b70ea5
+oid sha256:eca5c37204b362a441b3273f38452b4386b84ee7619b666d4b3b0e16c8fe8005
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0fd1da2876a8ac3c78a5e4ba1b25ab57bc9fb8b9d784343ae3a00a2b57b1790
+oid sha256:3f8da2f4f83922aefb3d0fee39f3f0e3ef10681d4b715072894808ccd67313c8
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbef7b3481c8719e4fd8401275e981037f23955690e35f3ff0a3d57cc3641182
+oid sha256:f7c3465e53225cf47a0452e207cbdd32c062905ce002446e7d89193480ef7e0e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3530e708a0a3625e6818dd6eac0a54ff3b9bf9b0959a321355a2a6b89ff733c2
+oid sha256:81183b684712db2a14af56028901f1bcacabf49942f252bd058ca9e6f6c6f782
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6c96dd843c4f978a88f67c059b44246cb4b08a47f2ae5fb05100289b50d807
+oid sha256:f7f27170d84436cfb9e7823b307ac9fef0dd654599d3ed2bea3f958f16c3f263
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182928c4d9d9c02600d4fe95362b2ca2a6fe014bd67bf7189a147a776e90d327
+oid sha256:a8aefe930258d887b8299317fd4e4f2c27edb96cb0c4188808d354917ed36145
 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": 1.0288419723510742,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8032128514056225,
+  "best_metric": 0.9987742304801941,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.606425702811245,
   "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": 35.339,
       "eval_steps_per_second": 4.544,
       "step": 25
+    },
+    {
+      "epoch": 0.8353413654618473,
+      "grad_norm": 0.17465923726558685,
+      "learning_rate": 5e-05,
+      "loss": 0.9016,
+      "step": 26
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 0.1872902363538742,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8917,
+      "step": 27
+    },
+    {
+      "epoch": 0.8995983935742972,
+      "grad_norm": 0.18722985684871674,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0243,
+      "step": 28
+    },
+    {
+      "epoch": 0.9317269076305221,
+      "grad_norm": 0.2619907855987549,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1796,
+      "step": 29
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.31004104018211365,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1372,
+      "step": 30
+    },
+    {
+      "epoch": 0.9959839357429718,
+      "grad_norm": 0.6074375510215759,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1173,
+      "step": 31
+    },
+    {
+      "epoch": 1.0281124497991967,
+      "grad_norm": 0.514019787311554,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7883,
+      "step": 32
+    },
+    {
+      "epoch": 1.0602409638554218,
+      "grad_norm": 0.23374691605567932,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8339,
+      "step": 33
+    },
+    {
+      "epoch": 1.0923694779116466,
+      "grad_norm": 0.2548729479312897,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8329,
+      "step": 34
+    },
+    {
+      "epoch": 1.1244979919678715,
+      "grad_norm": 0.2810096740722656,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9055,
+      "step": 35
+    },
+    {
+      "epoch": 1.1566265060240963,
+      "grad_norm": 0.355925977230072,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0052,
+      "step": 36
+    },
+    {
+      "epoch": 1.1887550200803212,
+      "grad_norm": 0.4292905330657959,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1282,
+      "step": 37
+    },
+    {
+      "epoch": 1.2208835341365463,
+      "grad_norm": 0.49879974126815796,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0253,
+      "step": 38
+    },
+    {
+      "epoch": 1.2530120481927711,
+      "grad_norm": 0.27068158984184265,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6199,
+      "step": 39
+    },
+    {
+      "epoch": 1.285140562248996,
+      "grad_norm": 0.260896772146225,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9507,
+      "step": 40
+    },
+    {
+      "epoch": 1.3172690763052208,
+      "grad_norm": 0.26006272435188293,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8103,
+      "step": 41
+    },
+    {
+      "epoch": 1.3493975903614457,
+      "grad_norm": 0.27475443482398987,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8499,
+      "step": 42
+    },
+    {
+      "epoch": 1.3815261044176708,
+      "grad_norm": 0.3011744022369385,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9216,
+      "step": 43
+    },
+    {
+      "epoch": 1.4136546184738956,
+      "grad_norm": 0.37961646914482117,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0301,
+      "step": 44
+    },
+    {
+      "epoch": 1.4457831325301205,
+      "grad_norm": 0.4721483886241913,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1092,
+      "step": 45
+    },
+    {
+      "epoch": 1.4779116465863453,
+      "grad_norm": 0.5502549409866333,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.066,
+      "step": 46
+    },
+    {
+      "epoch": 1.5100401606425704,
+      "grad_norm": 0.28434449434280396,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7651,
+      "step": 47
+    },
+    {
+      "epoch": 1.5421686746987953,
+      "grad_norm": 0.2478226125240326,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8829,
+      "step": 48
+    },
+    {
+      "epoch": 1.5742971887550201,
+      "grad_norm": 0.25373923778533936,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8507,
+      "step": 49
+    },
+    {
+      "epoch": 1.606425702811245,
+      "grad_norm": 0.2824363708496094,
+      "learning_rate": 0.0,
+      "loss": 0.8463,
+      "step": 50
+    },
+    {
+      "epoch": 1.606425702811245,
+      "eval_loss": 0.9987742304801941,
+      "eval_runtime": 5.9338,
+      "eval_samples_per_second": 35.391,
+      "eval_steps_per_second": 4.55,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null