Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a6e7948015617db6f59b212a06ea930f700b7cdf4f71e4798f0332d03de1c8
+oid sha256:0a8e51038654fa4667db3d5c7b730a8571806939937b73c2dd4d4f316584ae5a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7935156af1dee9a1380669064a5a6dd3f808bfdf2134b5f5c577a4d80d2e3dc8
+oid sha256:8666fddcf864e81dba70144e5ce0e24e8b88ecd6b2f4d483dee8b43cb7db2b0c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e81d4e795057df173963e8a729d7790a3915ff147b1766aff7d48321a7a079
+oid sha256:fb87c51cab1f8275c3e7de132a3cd6787ba4d1f9fc187e3b7479f91898558a77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83e1eac183ba68364d7f3d0e07866ddcb42c40fae7a05df070bc0689b2cdb86
+oid sha256:851fbdc70fe178c68b0b0653919a5e7c83a418f6b8b70ab851b36884a0f204bf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8435b914fa6266a97be1a9417d543c29c90615fa58e781014c1d12c32737fcf3
+oid sha256:012e58392be8c72e610cc2e4a09be0c68e0ac534a2864ab4352bff6f8d52e758
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef027b47bedf569883ae5bc0b737888e11675ac76533e029fa97c9dac15eff4
+oid sha256:d2ac9a2cb8dbdbaf0ffc57ca1acfb8c37956f1ccae5cc714bb3e107e966e84a9
 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": 1.0928798913955688,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.041788549937317176,
+  "best_metric": 0.9791784286499023,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08357709987463435,
   "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": 33.708,
       "eval_steps_per_second": 4.215,
       "step": 25
+    },
+    {
+      "epoch": 0.04346009193480986,
+      "grad_norm": 84.98091888427734,
+      "learning_rate": 5e-05,
+      "loss": 22.1274,
+      "step": 26
+    },
+    {
+      "epoch": 0.04513163393230255,
+      "grad_norm": 48.58253860473633,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 18.1724,
+      "step": 27
+    },
+    {
+      "epoch": 0.046803175929795236,
+      "grad_norm": 47.83669662475586,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 18.7154,
+      "step": 28
+    },
+    {
+      "epoch": 0.04847471792728792,
+      "grad_norm": 28.590259552001953,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 17.4828,
+      "step": 29
+    },
+    {
+      "epoch": 0.05014625992478061,
+      "grad_norm": 38.26438903808594,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 16.6586,
+      "step": 30
+    },
+    {
+      "epoch": 0.051817801922273296,
+      "grad_norm": 32.16006088256836,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 16.3044,
+      "step": 31
+    },
+    {
+      "epoch": 0.05348934391976599,
+      "grad_norm": 26.799610137939453,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 16.085,
+      "step": 32
+    },
+    {
+      "epoch": 0.05516088591725867,
+      "grad_norm": 14.574356079101562,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 15.5434,
+      "step": 33
+    },
+    {
+      "epoch": 0.056832427914751356,
+      "grad_norm": 12.779386520385742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 15.5748,
+      "step": 34
+    },
+    {
+      "epoch": 0.05850396991224405,
+      "grad_norm": 13.018362998962402,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 15.3028,
+      "step": 35
+    },
+    {
+      "epoch": 0.06017551190973673,
+      "grad_norm": 12.1093111038208,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 15.2333,
+      "step": 36
+    },
+    {
+      "epoch": 0.06184705390722942,
+      "grad_norm": 13.116833686828613,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 14.8206,
+      "step": 37
+    },
+    {
+      "epoch": 0.0635185959047221,
+      "grad_norm": 29.25300407409668,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 17.432,
+      "step": 38
+    },
+    {
+      "epoch": 0.0651901379022148,
+      "grad_norm": 19.870817184448242,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 16.8838,
+      "step": 39
+    },
+    {
+      "epoch": 0.06686167989970748,
+      "grad_norm": 23.810110092163086,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 17.8457,
+      "step": 40
+    },
+    {
+      "epoch": 0.06853322189720017,
+      "grad_norm": 13.098806381225586,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 16.3933,
+      "step": 41
+    },
+    {
+      "epoch": 0.07020476389469285,
+      "grad_norm": 12.435422897338867,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 16.2141,
+      "step": 42
+    },
+    {
+      "epoch": 0.07187630589218554,
+      "grad_norm": 12.03013801574707,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 15.7677,
+      "step": 43
+    },
+    {
+      "epoch": 0.07354784788967823,
+      "grad_norm": 10.967927932739258,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.3767,
+      "step": 44
+    },
+    {
+      "epoch": 0.07521938988717092,
+      "grad_norm": 12.3696870803833,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 15.3364,
+      "step": 45
+    },
+    {
+      "epoch": 0.0768909318846636,
+      "grad_norm": 12.121807098388672,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 15.4199,
+      "step": 46
+    },
+    {
+      "epoch": 0.07856247388215629,
+      "grad_norm": 11.486431121826172,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 14.7235,
+      "step": 47
+    },
+    {
+      "epoch": 0.08023401587964897,
+      "grad_norm": 15.480917930603027,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 15.3093,
+      "step": 48
+    },
+    {
+      "epoch": 0.08190555787714167,
+      "grad_norm": 19.982593536376953,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 14.56,
+      "step": 49
+    },
+    {
+      "epoch": 0.08357709987463435,
+      "grad_norm": 32.05732727050781,
+      "learning_rate": 0.0,
+      "loss": 14.2789,
+      "step": 50
+    },
+    {
+      "epoch": 0.08357709987463435,
+      "eval_loss": 0.9791784286499023,
+      "eval_runtime": 119.0554,
+      "eval_samples_per_second": 33.858,
+      "eval_steps_per_second": 4.233,
+      "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": 3.097766669288735e+17,
+  "total_flos": 6.246809181450404e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null