Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143857263e13a89652986152a3b0607a92b6e688cc9938432a34ac914b004919
+oid sha256:461ebaab725e161d6ab27b50c209643fe86a602143a3b4d684f707603a637a8f
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25abb81cd3ec52e239884cde1c50e6cf437354d6cdc4074bc5445bca4b1d5a1a
+oid sha256:87638cba275e3f46fa97890aed4c52dd7e080f332ad0e5a7690d077aaf74050b
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc22d57a1fdc2a85495b03514d75d2469fb07041c19af26ff4e91cab00719766
+oid sha256:03854391761aeaff8f7b32622b9ab5b81a444e0af20904b5ec24c28843f29325
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e9dbe041740d1e0efc7b7da9737745f7117efc504aff6920069eeb20ea282e
+oid sha256:57f5d28714d6a1739d20d052a48b0fcb91761747d906075840e78ad156cf5578
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8009df9ef28d8d8bcd21b1306f2d701d33e280aca2a7110002a8dd13b176bbbf
+oid sha256:19009ed266cbd1a795eba36b2308114a133896143589ccd72ea999f950d02a71
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45840bb4b2b646a80d8b64c6e68d2124bf3e5888fe48f47b816f400a3617f4eb
+oid sha256:e702bc53ff7c610f59c0ed1404ef1b96f8fe5129cd1750f9ee175cb62d499cca
 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": 0.726329505443573,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11392765593847906,
+  "best_metric": 0.6951894164085388,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22785531187695812,
   "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": 23.56,
       "eval_steps_per_second": 6.126,
       "step": 25
+    },
+    {
+      "epoch": 0.11848476217601824,
+      "grad_norm": 2.477088689804077,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.1875,
+      "step": 26
+    },
+    {
+      "epoch": 0.1230418684135574,
+      "grad_norm": 2.374391555786133,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7398,
+      "step": 27
+    },
+    {
+      "epoch": 0.12759897465109654,
+      "grad_norm": 2.537091016769409,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7191,
+      "step": 28
+    },
+    {
+      "epoch": 0.13215608088863573,
+      "grad_norm": 2.4189252853393555,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7205,
+      "step": 29
+    },
+    {
+      "epoch": 0.1367131871261749,
+      "grad_norm": 2.188260793685913,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.0926,
+      "step": 30
+    },
+    {
+      "epoch": 0.14127029336371405,
+      "grad_norm": 2.1279513835906982,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.709,
+      "step": 31
+    },
+    {
+      "epoch": 0.1458273996012532,
+      "grad_norm": 2.162879705429077,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.5126,
+      "step": 32
+    },
+    {
+      "epoch": 0.15038450583879237,
+      "grad_norm": 4.307819843292236,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.5518,
+      "step": 33
+    },
+    {
+      "epoch": 0.15494161207633153,
+      "grad_norm": 2.7188963890075684,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.9315,
+      "step": 34
+    },
+    {
+      "epoch": 0.1594987183138707,
+      "grad_norm": 3.0349268913269043,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.0043,
+      "step": 35
+    },
+    {
+      "epoch": 0.16405582455140985,
+      "grad_norm": 4.643979072570801,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 12.3598,
+      "step": 36
+    },
+    {
+      "epoch": 0.168612930788949,
+      "grad_norm": 6.440622329711914,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.8752,
+      "step": 37
+    },
+    {
+      "epoch": 0.17317003702648817,
+      "grad_norm": 4.075384616851807,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 9.3186,
+      "step": 38
+    },
+    {
+      "epoch": 0.17772714326402733,
+      "grad_norm": 1.565960168838501,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.3988,
+      "step": 39
+    },
+    {
+      "epoch": 0.1822842495015665,
+      "grad_norm": 1.775325059890747,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.5951,
+      "step": 40
+    },
+    {
+      "epoch": 0.18684135573910568,
+      "grad_norm": 1.5518596172332764,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.3133,
+      "step": 41
+    },
+    {
+      "epoch": 0.19139846197664484,
+      "grad_norm": 1.7390590906143188,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.4181,
+      "step": 42
+    },
+    {
+      "epoch": 0.195955568214184,
+      "grad_norm": 1.728224277496338,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.6342,
+      "step": 43
+    },
+    {
+      "epoch": 0.20051267445172316,
+      "grad_norm": 1.828178882598877,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.1649,
+      "step": 44
+    },
+    {
+      "epoch": 0.20506978068926232,
+      "grad_norm": 1.769647240638733,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3964,
+      "step": 45
+    },
+    {
+      "epoch": 0.20962688692680148,
+      "grad_norm": 2.0480496883392334,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.366,
+      "step": 46
+    },
+    {
+      "epoch": 0.21418399316434064,
+      "grad_norm": 2.396080732345581,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.6168,
+      "step": 47
+    },
+    {
+      "epoch": 0.2187410994018798,
+      "grad_norm": 2.990973711013794,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.1925,
+      "step": 48
+    },
+    {
+      "epoch": 0.22329820563941896,
+      "grad_norm": 5.037263870239258,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 9.9783,
+      "step": 49
+    },
+    {
+      "epoch": 0.22785531187695812,
+      "grad_norm": 6.590723991394043,
+      "learning_rate": 1e-05,
+      "loss": 7.5131,
+      "step": 50
+    },
+    {
+      "epoch": 0.22785531187695812,
+      "eval_loss": 0.6951894164085388,
+      "eval_runtime": 2.1209,
+      "eval_samples_per_second": 23.575,
+      "eval_steps_per_second": 6.13,
+      "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": 2,
   "trial_name": null,
   "trial_params": null