Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8d99b05858382157023c82f21853f2b848a0f95e44a26eb25f096ec81206cf
+oid sha256:bd80b4cb4c91028bad0b2afe9044dc91821ff52f9c4ef54a9465504b26880352
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850698c3a9b678f440ba536bb53cf85fa03d3d7d6335e39da1de080abfce71c0
+oid sha256:0d1033e6b6f1f0154fbadfe2ca2b0d5da3c6baf74be509614f7e096c3d4f630b
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd65ede5df3663605e59476f31baab8ef7b443bd706ed5c744fce11ace9577e
+oid sha256:6c50a21132f924567ccba77e7133ddd70402cd06edd27c279c5d8c41fe3315ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e70d9c724887e2b0108625753de5f73236f640af1ee4acf8878cfcccb389e2
+oid sha256:bae679cfbc2f1e6cc04b2700acf9da379aa7b37152cd97bc57ca1abd2ae3d22f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028856fa0c0d89bef89656d78f38bd329001a9130513a8e852630b485fa75e3c
+oid sha256:83c657de37017ed669c821ae1560bc0b13bd42bcdd3ae76699d06f40464eaea2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12cda5465afc3ed821150e7792ce85efe6e5ed2a8cab9052349d6c236ef588c
+oid sha256:4aea80fe9db0529001f3324caaa7f925e1fe2ae82b9313923d75be4941850e52
 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": 0.7260035872459412,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11394388263780088,
+  "best_metric": 0.6943662762641907,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22788776527560176,
   "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": 11.681,
       "eval_steps_per_second": 3.037,
       "step": 25
+    },
+    {
+      "epoch": 0.11850163794331292,
+      "grad_norm": 4.842848777770996,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 22.3883,
+      "step": 26
+    },
+    {
+      "epoch": 0.12305939324882495,
+      "grad_norm": 4.692829608917236,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 23.4571,
+      "step": 27
+    },
+    {
+      "epoch": 0.12761714855433698,
+      "grad_norm": 5.017322063446045,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 23.4224,
+      "step": 28
+    },
+    {
+      "epoch": 0.13217490385984904,
+      "grad_norm": 4.82174825668335,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 23.4251,
+      "step": 29
+    },
+    {
+      "epoch": 0.13673265916536106,
+      "grad_norm": 4.154259204864502,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 22.2265,
+      "step": 30
+    },
+    {
+      "epoch": 0.1412904144708731,
+      "grad_norm": 4.162024974822998,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 21.3956,
+      "step": 31
+    },
+    {
+      "epoch": 0.14584816977638512,
+      "grad_norm": 4.216670513153076,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 22.98,
+      "step": 32
+    },
+    {
+      "epoch": 0.15040592508189718,
+      "grad_norm": 4.838366508483887,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 21.0222,
+      "step": 33
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 5.273548603057861,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 19.7755,
+      "step": 34
+    },
+    {
+      "epoch": 0.15952143569292124,
+      "grad_norm": 5.883111000061035,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 19.9225,
+      "step": 35
+    },
+    {
+      "epoch": 0.16407919099843327,
+      "grad_norm": 9.225810050964355,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 24.6943,
+      "step": 36
+    },
+    {
+      "epoch": 0.1686369463039453,
+      "grad_norm": 13.115874290466309,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 13.7088,
+      "step": 37
+    },
+    {
+      "epoch": 0.17319470160945735,
+      "grad_norm": 8.241169929504395,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.6438,
+      "step": 38
+    },
+    {
+      "epoch": 0.17775245691496938,
+      "grad_norm": 3.0531914234161377,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 22.7809,
+      "step": 39
+    },
+    {
+      "epoch": 0.1823102122204814,
+      "grad_norm": 3.5217833518981934,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 23.1791,
+      "step": 40
+    },
+    {
+      "epoch": 0.18686796752599344,
+      "grad_norm": 3.0812361240386963,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 22.5931,
+      "step": 41
+    },
+    {
+      "epoch": 0.1914257228315055,
+      "grad_norm": 3.4206924438476562,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 22.8819,
+      "step": 42
+    },
+    {
+      "epoch": 0.19598347813701752,
+      "grad_norm": 3.3050315380096436,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 21.2673,
+      "step": 43
+    },
+    {
+      "epoch": 0.20054123344252955,
+      "grad_norm": 3.533254384994507,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.2905,
+      "step": 44
+    },
+    {
+      "epoch": 0.20509898874804158,
+      "grad_norm": 3.4284398555755615,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 20.735,
+      "step": 45
+    },
+    {
+      "epoch": 0.2096567440535536,
+      "grad_norm": 4.47261381149292,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 22.6068,
+      "step": 46
+    },
+    {
+      "epoch": 0.21421449935906567,
+      "grad_norm": 4.796079158782959,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 21.1984,
+      "step": 47
+    },
+    {
+      "epoch": 0.2187722546645777,
+      "grad_norm": 5.997812271118164,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 22.3013,
+      "step": 48
+    },
+    {
+      "epoch": 0.22333000997008973,
+      "grad_norm": 10.26131534576416,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 19.959,
+      "step": 49
+    },
+    {
+      "epoch": 0.22788776527560176,
+      "grad_norm": 13.377036094665527,
+      "learning_rate": 1e-05,
+      "loss": 15.0867,
+      "step": 50
+    },
+    {
+      "epoch": 0.22788776527560176,
+      "eval_loss": 0.6943662762641907,
+      "eval_runtime": 4.2957,
+      "eval_samples_per_second": 11.639,
+      "eval_steps_per_second": 3.026,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null