Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db26e9e4df21c33e9869b34e86f872973e612723e39c420e043b1e1356a32e4
+oid sha256:5109a54f26f14f6c35b3d89509932f3a9cb58736cbe01224dac4bbfc9c102e13
 size 144748392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd89ac60a15daec02d734232eb788555a42a0363b51f9bd6dbc1d2985551d83b
+oid sha256:2fd7949bf4f37317c431182a1e8a508d7cb8a22469730e2a48d1217cab55fef5
 size 289690242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f655273aea42a76c8e6f865bcfe7aabf97cb943d786a731b32d814d3839a69
+oid sha256:fd26262066b582c6a1d35088dcf42a1df150f9bd1e7d219a4003e544a370ae8a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ceca4d8d17ef2ede1f70d9a868dd4c84d806cfeb5bd2516936df9e63e89deb
+oid sha256:91026414285dfab3bc00df6f10a9c3c0199f2e26d9f7ecbad47bb3b3fb758f5d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a13f0f4dc3a73510b37122a1027ee3f2b8c1955c379fbc58d9966cb0acf13328
+oid sha256:fc3d2f5886fbe7c504b8d23d1ececcffc0469b054a60395e0c291c1f0cd51069
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86e090157db4b240ac5b23ddd386eda5bd3eec3d3b89322a79f020f7af319c2
+oid sha256:a2bc55b067fb1e3aad17c5420566bacd03ce17a9517cb94921e3c5aaa682f574
 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": 3.8750054836273193,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3460207612456747,
+  "best_metric": 3.1890745162963867,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6920415224913494,
   "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": 78.439,
       "eval_steps_per_second": 9.825,
       "step": 25
+    },
+    {
+      "epoch": 0.35986159169550175,
+      "grad_norm": 1.2438147068023682,
+      "learning_rate": 5e-05,
+      "loss": 3.9151,
+      "step": 26
+    },
+    {
+      "epoch": 0.3737024221453287,
+      "grad_norm": 1.0506852865219116,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.7531,
+      "step": 27
+    },
+    {
+      "epoch": 0.3875432525951557,
+      "grad_norm": 1.0012786388397217,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.7794,
+      "step": 28
+    },
+    {
+      "epoch": 0.4013840830449827,
+      "grad_norm": 0.98823481798172,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.659,
+      "step": 29
+    },
+    {
+      "epoch": 0.41522491349480967,
+      "grad_norm": 1.0248918533325195,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.5903,
+      "step": 30
+    },
+    {
+      "epoch": 0.4290657439446367,
+      "grad_norm": 1.0814943313598633,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.4663,
+      "step": 31
+    },
+    {
+      "epoch": 0.4429065743944637,
+      "grad_norm": 1.1849011182785034,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.397,
+      "step": 32
+    },
+    {
+      "epoch": 0.45674740484429066,
+      "grad_norm": 1.5150214433670044,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.5301,
+      "step": 33
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.6340036392211914,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5942,
+      "step": 34
+    },
+    {
+      "epoch": 0.4844290657439446,
+      "grad_norm": 1.5461198091506958,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.4832,
+      "step": 35
+    },
+    {
+      "epoch": 0.4982698961937716,
+      "grad_norm": 1.5538333654403687,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.3929,
+      "step": 36
+    },
+    {
+      "epoch": 0.5121107266435986,
+      "grad_norm": 1.4813439846038818,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.3781,
+      "step": 37
+    },
+    {
+      "epoch": 0.5259515570934256,
+      "grad_norm": 1.2175124883651733,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5876,
+      "step": 38
+    },
+    {
+      "epoch": 0.5397923875432526,
+      "grad_norm": 1.1959764957427979,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.1674,
+      "step": 39
+    },
+    {
+      "epoch": 0.5536332179930796,
+      "grad_norm": 1.058384656906128,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.1204,
+      "step": 40
+    },
+    {
+      "epoch": 0.5674740484429066,
+      "grad_norm": 0.9045761227607727,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.2443,
+      "step": 41
+    },
+    {
+      "epoch": 0.5813148788927336,
+      "grad_norm": 1.022927165031433,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.1241,
+      "step": 42
+    },
+    {
+      "epoch": 0.5951557093425606,
+      "grad_norm": 0.936863899230957,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.0281,
+      "step": 43
+    },
+    {
+      "epoch": 0.6089965397923875,
+      "grad_norm": 0.9517385363578796,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1129,
+      "step": 44
+    },
+    {
+      "epoch": 0.6228373702422145,
+      "grad_norm": 1.131404161453247,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.2927,
+      "step": 45
+    },
+    {
+      "epoch": 0.6366782006920415,
+      "grad_norm": 1.437263011932373,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.3686,
+      "step": 46
+    },
+    {
+      "epoch": 0.6505190311418685,
+      "grad_norm": 1.5570812225341797,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.2489,
+      "step": 47
+    },
+    {
+      "epoch": 0.6643598615916955,
+      "grad_norm": 1.5820376873016357,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.3061,
+      "step": 48
+    },
+    {
+      "epoch": 0.6782006920415224,
+      "grad_norm": 1.4706281423568726,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.0915,
+      "step": 49
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "grad_norm": 1.5056296586990356,
+      "learning_rate": 0.0,
+      "loss": 3.5272,
+      "step": 50
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "eval_loss": 3.1890745162963867,
+      "eval_runtime": 6.2141,
+      "eval_samples_per_second": 78.37,
+      "eval_steps_per_second": 9.816,
+      "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": 6.50416267156521e+16,
+  "total_flos": 1.3004277953855488e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null