Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0034398b99a65e18e00e5855dedae8eff3ff57667209814886f573d931843c4c
+oid sha256:17c9b0f1de4930dd15e24546303135d2e365eba95aec62c52ac476395067fa6e
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3508bc2412d284e6fb5c06fc271e4b0c9eaf73595908f257b17bfa8d374a2e
+oid sha256:de11a217e7fd77c3ea4b532f71ecb95b726ee25de0a01b794135bd168140f42e
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71bdca4cd14651ea150c55bba4c4d66397e287764be618b8245b3b09227a629
+oid sha256:b61d32c3d15f96b5875482a9fd953db218138b751be4f79d36c48c1c208fbad8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaac621bba8bf01a2816a7d839f3ce62c075b4eec5c85bbb2580e6f61ec2e34
+oid sha256:0a3243fe63efc09faee93f827e3af48cb2f2e63cd1957bbae1fb9db43f2933a7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40314fd9c3e9b27a413d4bc52e68a03fe390ae56e91f2d998ee52539fd4b4488
+oid sha256:985938a634a2c11ede12207f0af190195c8d3c590edafdc0694ea66ff300e53b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71513efeae9cfe58b298c9c2f92cbebdf2f0dc6c22d06194cd60c0492fd4452
+oid sha256:0106a34affe5c79771ba67d410481b88e52c11d8eaea48649be33013d04db19d
 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": 1.0111019611358643,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5956813104988831,
+  "best_metric": 0.9392607808113098,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1943410275502606,
   "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": 12.526,
       "eval_steps_per_second": 3.257,
       "step": 25
+    },
+    {
+      "epoch": 0.6195085629188384,
+      "grad_norm": 0.4272650480270386,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8835,
+      "step": 26
+    },
+    {
+      "epoch": 0.6433358153387937,
+      "grad_norm": 0.4884018003940582,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8979,
+      "step": 27
+    },
+    {
+      "epoch": 0.6671630677587491,
+      "grad_norm": 0.4665274918079376,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8445,
+      "step": 28
+    },
+    {
+      "epoch": 0.6909903201787044,
+      "grad_norm": 0.47663161158561707,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.822,
+      "step": 29
+    },
+    {
+      "epoch": 0.7148175725986597,
+      "grad_norm": 0.4935821294784546,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7297,
+      "step": 30
+    },
+    {
+      "epoch": 0.7386448250186151,
+      "grad_norm": 0.3330288231372833,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1636,
+      "step": 31
+    },
+    {
+      "epoch": 0.7624720774385704,
+      "grad_norm": 0.39705488085746765,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4158,
+      "step": 32
+    },
+    {
+      "epoch": 0.7862993298585257,
+      "grad_norm": 0.41890138387680054,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2318,
+      "step": 33
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.4597773551940918,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0762,
+      "step": 34
+    },
+    {
+      "epoch": 0.8339538346984363,
+      "grad_norm": 0.4643116891384125,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9961,
+      "step": 35
+    },
+    {
+      "epoch": 0.8577810871183916,
+      "grad_norm": 0.38791903853416443,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8689,
+      "step": 36
+    },
+    {
+      "epoch": 0.8816083395383469,
+      "grad_norm": 0.39262112975120544,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8219,
+      "step": 37
+    },
+    {
+      "epoch": 0.9054355919583023,
+      "grad_norm": 0.35502174496650696,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8349,
+      "step": 38
+    },
+    {
+      "epoch": 0.9292628443782577,
+      "grad_norm": 0.3888930678367615,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9012,
+      "step": 39
+    },
+    {
+      "epoch": 0.953090096798213,
+      "grad_norm": 0.3541257381439209,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7204,
+      "step": 40
+    },
+    {
+      "epoch": 0.9769173492181683,
+      "grad_norm": 0.6055673360824585,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6248,
+      "step": 41
+    },
+    {
+      "epoch": 1.003723008190618,
+      "grad_norm": 0.3594631552696228,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4831,
+      "step": 42
+    },
+    {
+      "epoch": 1.0275502606105733,
+      "grad_norm": 0.31771546602249146,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3284,
+      "step": 43
+    },
+    {
+      "epoch": 1.0513775130305287,
+      "grad_norm": 0.3231451213359833,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1876,
+      "step": 44
+    },
+    {
+      "epoch": 1.075204765450484,
+      "grad_norm": 0.29634058475494385,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1231,
+      "step": 45
+    },
+    {
+      "epoch": 1.0990320178704394,
+      "grad_norm": 0.27380484342575073,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8992,
+      "step": 46
+    },
+    {
+      "epoch": 1.1228592702903946,
+      "grad_norm": 0.32522863149642944,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7892,
+      "step": 47
+    },
+    {
+      "epoch": 1.14668652271035,
+      "grad_norm": 0.3326983153820038,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8262,
+      "step": 48
+    },
+    {
+      "epoch": 1.1705137751303052,
+      "grad_norm": 0.32248544692993164,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8126,
+      "step": 49
+    },
+    {
+      "epoch": 1.1943410275502606,
+      "grad_norm": 0.3252665102481842,
+      "learning_rate": 1e-05,
+      "loss": 0.7998,
+      "step": 50
+    },
+    {
+      "epoch": 1.1943410275502606,
+      "eval_loss": 0.9392607808113098,
+      "eval_runtime": 3.9593,
+      "eval_samples_per_second": 12.628,
+      "eval_steps_per_second": 3.283,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null