Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225006b7c00682b26abae4733f44778d2875e014a68a15958f1c410540a332ef
+oid sha256:bfbfb492b20252f4caa4146e7cde6145b563bd4d4bab950754b99f4057c0bd1b
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827b529176076797064155510b614cc1bb429f4a3ba3e74a04fe590b6011dd5c
+oid sha256:47bc83229c3e9ba96d962e665ad3373c7b5a7e920ffc649cdc616de8887ea4f5
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a5707a52fe5b5f8b86ab291e3142e958ef7e137e54d9e507371a434e24174a
+oid sha256:76e61ab2bf9e586958859f6421fd73d184220125a752e20b2e4f398d44149919
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c89c7ab52964b97feedfebf9d647c0a6e4f201fa464f763d847bb87132850dd
+oid sha256:081f8e5490e2bdd42269262324fbd7a7aa639bd8462d2209dcc5d43f0a91d8e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0808f1aef8f8356f326607f1a4813faf2b7d7f3c98ec4cb26d3ef01d511fc82
+oid sha256:5cee113d9e4fc9ed2b02c4749ef8d4ddc70315acb4d1be57fef1fe6747c3113e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68800ef5e3fd2426a85a7e0e349f1d736fa92dcec6f0c9d73e1fcdfa605b8f16
+oid sha256:100f0aa0a28d9b7b5cca0864b7cb5d70edd4d5e3d4e1a317610f9ee5e85da24b
 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": 6.909616947174072,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1764705882352942,
+  "best_metric": 6.902400493621826,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.3529411764705883,
   "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": 1262.017,
       "eval_steps_per_second": 157.752,
       "step": 25
+    },
+    {
+      "epoch": 1.223529411764706,
+      "grad_norm": 0.2847910225391388,
+      "learning_rate": 5e-05,
+      "loss": 7.1571,
+      "step": 26
+    },
+    {
+      "epoch": 1.2705882352941176,
+      "grad_norm": 0.26297202706336975,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.7637,
+      "step": 27
+    },
+    {
+      "epoch": 1.3176470588235294,
+      "grad_norm": 0.23891142010688782,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.9968,
+      "step": 28
+    },
+    {
+      "epoch": 1.3647058823529412,
+      "grad_norm": 0.2524110674858093,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.9215,
+      "step": 29
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.2882583737373352,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.9027,
+      "step": 30
+    },
+    {
+      "epoch": 1.4588235294117646,
+      "grad_norm": 0.2517209053039551,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.9307,
+      "step": 31
+    },
+    {
+      "epoch": 1.5058823529411764,
+      "grad_norm": 0.29053542017936707,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.6777,
+      "step": 32
+    },
+    {
+      "epoch": 1.5529411764705883,
+      "grad_norm": 0.2220264971256256,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 7.0782,
+      "step": 33
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.25292810797691345,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.85,
+      "step": 34
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.2669088840484619,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 7.079,
+      "step": 35
+    },
+    {
+      "epoch": 1.6941176470588235,
+      "grad_norm": 0.26724597811698914,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.7008,
+      "step": 36
+    },
+    {
+      "epoch": 1.7411764705882353,
+      "grad_norm": 0.266480028629303,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.7112,
+      "step": 37
+    },
+    {
+      "epoch": 1.788235294117647,
+      "grad_norm": 0.23365375399589539,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.256,
+      "step": 38
+    },
+    {
+      "epoch": 1.835294117647059,
+      "grad_norm": 0.25366276502609253,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.8007,
+      "step": 39
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.24693305790424347,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.9905,
+      "step": 40
+    },
+    {
+      "epoch": 1.9294117647058824,
+      "grad_norm": 0.2845700681209564,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.7647,
+      "step": 41
+    },
+    {
+      "epoch": 1.9764705882352942,
+      "grad_norm": 0.2774038016796112,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.0531,
+      "step": 42
+    },
+    {
+      "epoch": 2.023529411764706,
+      "grad_norm": 0.42704179883003235,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9847,
+      "step": 43
+    },
+    {
+      "epoch": 2.070588235294118,
+      "grad_norm": 0.22592473030090332,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.018,
+      "step": 44
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.21758249402046204,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 6.7623,
+      "step": 45
+    },
+    {
+      "epoch": 2.164705882352941,
+      "grad_norm": 0.23572538793087006,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.8807,
+      "step": 46
+    },
+    {
+      "epoch": 2.211764705882353,
+      "grad_norm": 0.2834058701992035,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.9006,
+      "step": 47
+    },
+    {
+      "epoch": 2.2588235294117647,
+      "grad_norm": 0.25600162148475647,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.7102,
+      "step": 48
+    },
+    {
+      "epoch": 2.3058823529411763,
+      "grad_norm": 0.2182091921567917,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 7.1599,
+      "step": 49
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.22837752103805542,
+      "learning_rate": 0.0,
+      "loss": 6.9719,
+      "step": 50
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 6.902400493621826,
+      "eval_runtime": 0.1136,
+      "eval_samples_per_second": 1267.459,
+      "eval_steps_per_second": 158.432,
+      "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": 2920736931840.0,
+  "total_flos": 5830775193600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null