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:f4c5f74b0280c7c5fc4cf3a77a42bebe27c63067232339284cf324ad4320cf2c
+oid sha256:c783b2c706bc487afacc2bd6e2e110b3e0c765313f23f070c4199aa9e1a82b4f
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f984275169c300ae76901924902ccdea42b2bbc2522c8008bc77e75566553c5b
+oid sha256:9fc83e7eafecc279f87b684bb1b8d7bf21dd8a38d937161e037468538cb26798
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d05b34b8afa274c1c41420ceecd329d23d5a1325e5322939899894ed23eece
+oid sha256:9e2368b437e1bd6a1dd2dc792e992c0ac10a38c76487615ecbb8fa0ba427736b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ca9cff6a9ea9b8f4200866a2a50ffd7d56201f9c9b79f9ad5fe271ce8012e2
+oid sha256:cae1c259d74b90fca8e34de18f0f5347b3644ec02e326d966684378152fb82a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecedd442276bba90918b93508ab815cd5e2cdb5e58eb4f6d5ef3f6fde5e44f64
+oid sha256:07bc9c7f3307ed5b6b5b504a78e2612c3f91c2608c621297108f23a13098bf46
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aeb1c4763842285de98d827a88a3c516904476e4edd455eebc5be1d074322d1
+oid sha256:c04900c118b4d496eb6fd3123db20ddc486ab8b01af8d3c5205e1bbce4be5720
 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": 1.0094516277313232,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022370113528326158,
+  "best_metric": 0.9958183765411377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.044740227056652315,
   "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": 14.722,
       "eval_steps_per_second": 3.828,
       "step": 25
+    },
+    {
+      "epoch": 0.0232649180694592,
+      "grad_norm": 0.5019625425338745,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9572,
+      "step": 26
+    },
+    {
+      "epoch": 0.02415972261059225,
+      "grad_norm": 0.5243887901306152,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.982,
+      "step": 27
+    },
+    {
+      "epoch": 0.025054527151725296,
+      "grad_norm": 0.5398479104042053,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.937,
+      "step": 28
+    },
+    {
+      "epoch": 0.025949331692858343,
+      "grad_norm": 0.5993919968605042,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9682,
+      "step": 29
+    },
+    {
+      "epoch": 0.026844136233991386,
+      "grad_norm": 0.534296452999115,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9194,
+      "step": 30
+    },
+    {
+      "epoch": 0.027738940775124434,
+      "grad_norm": 0.5929005742073059,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9588,
+      "step": 31
+    },
+    {
+      "epoch": 0.02863374531625748,
+      "grad_norm": 0.5979087352752686,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9557,
+      "step": 32
+    },
+    {
+      "epoch": 0.029528549857390528,
+      "grad_norm": 0.5713499784469604,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9217,
+      "step": 33
+    },
+    {
+      "epoch": 0.03042335439852357,
+      "grad_norm": 0.6617943048477173,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9979,
+      "step": 34
+    },
+    {
+      "epoch": 0.03131815893965662,
+      "grad_norm": 0.6407080292701721,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9964,
+      "step": 35
+    },
+    {
+      "epoch": 0.03221296348078966,
+      "grad_norm": 0.6977891325950623,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.944,
+      "step": 36
+    },
+    {
+      "epoch": 0.03310776802192271,
+      "grad_norm": 0.6950139403343201,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9345,
+      "step": 37
+    },
+    {
+      "epoch": 0.03400257256305576,
+      "grad_norm": 0.5052092671394348,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9109,
+      "step": 38
+    },
+    {
+      "epoch": 0.034897377104188804,
+      "grad_norm": 0.47866344451904297,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9576,
+      "step": 39
+    },
+    {
+      "epoch": 0.03579218164532185,
+      "grad_norm": 0.4459432065486908,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9317,
+      "step": 40
+    },
+    {
+      "epoch": 0.0366869861864549,
+      "grad_norm": 0.505197286605835,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9577,
+      "step": 41
+    },
+    {
+      "epoch": 0.037581790727587945,
+      "grad_norm": 0.5025796294212341,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9043,
+      "step": 42
+    },
+    {
+      "epoch": 0.03847659526872099,
+      "grad_norm": 0.5344678163528442,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9197,
+      "step": 43
+    },
+    {
+      "epoch": 0.03937139980985403,
+      "grad_norm": 0.5904696583747864,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9859,
+      "step": 44
+    },
+    {
+      "epoch": 0.04026620435098708,
+      "grad_norm": 0.6027600169181824,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9812,
+      "step": 45
+    },
+    {
+      "epoch": 0.04116100889212013,
+      "grad_norm": 0.6179023385047913,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9288,
+      "step": 46
+    },
+    {
+      "epoch": 0.042055813433253174,
+      "grad_norm": 0.6149353981018066,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9331,
+      "step": 47
+    },
+    {
+      "epoch": 0.04295061797438622,
+      "grad_norm": 0.6846910715103149,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9474,
+      "step": 48
+    },
+    {
+      "epoch": 0.04384542251551927,
+      "grad_norm": 0.6909250020980835,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.925,
+      "step": 49
+    },
+    {
+      "epoch": 0.044740227056652315,
+      "grad_norm": 0.7580010890960693,
+      "learning_rate": 1e-05,
+      "loss": 0.938,
+      "step": 50
+    },
+    {
+      "epoch": 0.044740227056652315,
+      "eval_loss": 0.9958183765411377,
+      "eval_runtime": 3.3791,
+      "eval_samples_per_second": 14.797,
+      "eval_steps_per_second": 3.847,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null