Training in progress, step 1950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04d5fa41fa6f39ff0e99d56a6427bf17f28fc57677e4371c961796044f5d2a3
+oid sha256:558bd7240ae36bf407fa59d99bc87b4f2a83238e3eefe9e7d80228b0d675c5f2
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccaaf38526637635b1485eaad8168918d1ff4276d494189eacd7059d25f24082
+oid sha256:c9c44e87a84da7f09944098b8b24a46d1e1784343e14aa00f21290dad1d35d03
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f11fbb1dc348e5245b6e67b90b53d052aa55ce6bbd45d7369c3c11528ee140
+oid sha256:b99872e409bc674b8b81f4e59047c6dd181202eceec2bd8ec5e0879c5adbc8fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8b759658b308282d06846d4dfda31388c652c687853c092da47be547d0736c
+oid sha256:b4b6379912da098573e94d032fbbd0f173cdb17e7336f428aac213f60f9a5145
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7177689671516418,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 78.26086956521739,
+  "epoch": 84.78260869565217,
   "eval_steps": 150,
-  "global_step": 1800,
+  "global_step": 1950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1747,6 +1747,151 @@
       "EMA_steps_per_second": 24.55,
       "epoch": 78.26086956521739,
       "step": 1800
+    },
+    {
+      "epoch": 78.69565217391305,
+      "grad_norm": 1.2506405115127563,
+      "learning_rate": 1.4978160876532222e-05,
+      "loss": 0.2825,
+      "step": 1810
+    },
+    {
+      "epoch": 79.1304347826087,
+      "grad_norm": 1.9981244802474976,
+      "learning_rate": 1.4978007989653455e-05,
+      "loss": 0.2405,
+      "step": 1820
+    },
+    {
+      "epoch": 79.56521739130434,
+      "grad_norm": 1.615986704826355,
+      "learning_rate": 1.4977852135168293e-05,
+      "loss": 0.2606,
+      "step": 1830
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 1.8828160762786865,
+      "learning_rate": 1.4977693313138507e-05,
+      "loss": 0.3032,
+      "step": 1840
+    },
+    {
+      "epoch": 80.43478260869566,
+      "grad_norm": 2.1056859493255615,
+      "learning_rate": 1.4977531523627054e-05,
+      "loss": 0.28,
+      "step": 1850
+    },
+    {
+      "epoch": 80.8695652173913,
+      "grad_norm": 1.2708007097244263,
+      "learning_rate": 1.4977366766698058e-05,
+      "loss": 0.2793,
+      "step": 1860
+    },
+    {
+      "epoch": 81.30434782608695,
+      "grad_norm": 1.5546568632125854,
+      "learning_rate": 1.4977199042416822e-05,
+      "loss": 0.231,
+      "step": 1870
+    },
+    {
+      "epoch": 81.73913043478261,
+      "grad_norm": 1.5425999164581299,
+      "learning_rate": 1.4977028350849831e-05,
+      "loss": 0.306,
+      "step": 1880
+    },
+    {
+      "epoch": 82.17391304347827,
+      "grad_norm": 1.6000920534133911,
+      "learning_rate": 1.4976854692064739e-05,
+      "loss": 0.2147,
+      "step": 1890
+    },
+    {
+      "epoch": 82.6086956521739,
+      "grad_norm": 1.8370901346206665,
+      "learning_rate": 1.497667806613038e-05,
+      "loss": 0.2592,
+      "step": 1900
+    },
+    {
+      "epoch": 83.04347826086956,
+      "grad_norm": 1.573868989944458,
+      "learning_rate": 1.497649847311676e-05,
+      "loss": 0.3003,
+      "step": 1910
+    },
+    {
+      "epoch": 83.47826086956522,
+      "grad_norm": 1.478338599205017,
+      "learning_rate": 1.4976315913095068e-05,
+      "loss": 0.2651,
+      "step": 1920
+    },
+    {
+      "epoch": 83.91304347826087,
+      "grad_norm": 2.278778076171875,
+      "learning_rate": 1.4976130386137666e-05,
+      "loss": 0.3041,
+      "step": 1930
+    },
+    {
+      "epoch": 84.34782608695652,
+      "grad_norm": 1.6957610845565796,
+      "learning_rate": 1.4975941892318084e-05,
+      "loss": 0.2639,
+      "step": 1940
+    },
+    {
+      "epoch": 84.78260869565217,
+      "grad_norm": 2.2558460235595703,
+      "learning_rate": 1.497575043171104e-05,
+      "loss": 0.2798,
+      "step": 1950
+    },
+    {
+      "epoch": 84.78260869565217,
+      "eval_loss": 0.8924320340156555,
+      "eval_runtime": 0.4145,
+      "eval_samples_per_second": 24.125,
+      "eval_steps_per_second": 24.125,
+      "step": 1950
+    },
+    {
+      "Start_State_loss": 0.861186683177948,
+      "Start_State_runtime": 0.4181,
+      "Start_State_samples_per_second": 23.92,
+      "Start_State_steps_per_second": 23.92,
+      "epoch": 84.78260869565217,
+      "step": 1950
+    },
+    {
+      "Raw_Model_loss": 0.8924320340156555,
+      "Raw_Model_runtime": 0.3985,
+      "Raw_Model_samples_per_second": 25.093,
+      "Raw_Model_steps_per_second": 25.093,
+      "epoch": 84.78260869565217,
+      "step": 1950
+    },
+    {
+      "SWA_loss": 0.740094780921936,
+      "SWA_runtime": 0.4024,
+      "SWA_samples_per_second": 24.849,
+      "SWA_steps_per_second": 24.849,
+      "epoch": 84.78260869565217,
+      "step": 1950
+    },
+    {
+      "EMA_loss": 0.8611790537834167,
+      "EMA_runtime": 0.3965,
+      "EMA_samples_per_second": 25.224,
+      "EMA_steps_per_second": 25.224,
+      "epoch": 84.78260869565217,
+      "step": 1950
     }
   ],
   "logging_steps": 10,
@@ -1766,7 +1911,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.631084552967782e+16,
+  "total_flos": 5.02053291067392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null