Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271e272f3f98dafac54eabf65fe7c941a42e4c849ca7ed4c3839a08fa408499d
+oid sha256:b2ab1b54ce042c169c01101e1c005c36e39e3afd27d938891c20b92f985d53f5
 size 29034840

last-checkpoint/global_step900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ab9661acad608360251cd89464cc408f3343f6a7634f3c53194ae61b4ad6ca
+size 43429616

last-checkpoint/global_step900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991672111a64fc25c5a9806fb82a4dabace627f936699d415624fca96d8fed70
+size 43429616

last-checkpoint/global_step900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f24af34e2730da78f3ab121c6577278e01e97404fe514680d4605dbf3d1921
+size 43429616

last-checkpoint/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ed897301f2520e1e17f77facfeb1296b22de983380d387aa2a0f24c54079af
+size 43429616

last-checkpoint/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7162c4e09532f9490922bccb0dbbcfe539972e0f3d49af32428a76030c053274
+size 637299

last-checkpoint/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1fabfaa7ff216589f1f45e0de64de68782d934b86fc832996ada7c681c3bd9
+size 637171

last-checkpoint/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68864aa3523e8a7232f1228e6e0dba67ac184874fa8332362ced37b3cbe041a
+size 637171

last-checkpoint/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834a420bd57a2a0fe552734d61c0bcc178574ff6e356d461ed6815bc79695c74
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step850
+global_step900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c9044354f826de248840acaaec171f816609c147a664089731a0570deef948
+oid sha256:b8f22ced19e790cc864cefe3b7c711d9ae631c44f95d42fb4829688cc3de0153
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f4c4013326db4e7267b656aaf72b86570f8aeee91ad39242a416cf8b963191
+oid sha256:3e0407513eba77d34cbf3adf0e59a58bd80716f4f00f414854253637e82be43d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e910793831957d8685c316138c33eef8867edf60052477dc9ad6ec0c6da901
+oid sha256:6060636c023258ce9b965e244b8a58b4c99d5784dde4405b39737550ef50cd4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfd0d71ef5a6c58d9f1d46851f4b1e699ca8a50ab3223cfb39668895cffeef2
+oid sha256:c24ccdfdcde39cb2265c82c50c36ffdfcc670f757aba4bcf4bb0fdc6d1373c4c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb2a3d4eafda026308c94c6ad3628bdceb63f20926d1a2696b97a46e83370c4
+oid sha256:7328934baedc90cac30c0635b4180443bb56c44db13a6f9445a42e3e72e30189
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4665524661540985,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-750",
-  "epoch": 0.2511078286558346,
+  "epoch": 0.2658788774002954,
   "eval_steps": 50,
-  "global_step": 850,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,11 +1520,100 @@
       "eval_steps_per_second": 0.785,
       "num_input_tokens_seen": 8822832,
       "step": 850
+    },
+    {
+      "epoch": 0.25258493353028066,
+      "grad_norm": 8.111385407981246,
+      "learning_rate": 9.841991170128374e-05,
+      "loss": 0.4636,
+      "num_input_tokens_seen": 8875608,
+      "step": 855
+    },
+    {
+      "epoch": 0.25406203840472674,
+      "grad_norm": 4.789169716538139,
+      "learning_rate": 9.838930774181285e-05,
+      "loss": 0.4322,
+      "num_input_tokens_seen": 8927600,
+      "step": 860
+    },
+    {
+      "epoch": 0.2555391432791728,
+      "grad_norm": 3.6029916519925167,
+      "learning_rate": 9.835841509221725e-05,
+      "loss": 0.4302,
+      "num_input_tokens_seen": 8980224,
+      "step": 865
+    },
+    {
+      "epoch": 0.2570162481536189,
+      "grad_norm": 17.138905616592684,
+      "learning_rate": 9.83272339368022e-05,
+      "loss": 0.5231,
+      "num_input_tokens_seen": 9032112,
+      "step": 870
+    },
+    {
+      "epoch": 0.258493353028065,
+      "grad_norm": 6.810210745159563,
+      "learning_rate": 9.829576446159416e-05,
+      "loss": 0.4414,
+      "num_input_tokens_seen": 9084480,
+      "step": 875
+    },
+    {
+      "epoch": 0.25997045790251105,
+      "grad_norm": 6.785950897404188,
+      "learning_rate": 9.826400685433968e-05,
+      "loss": 0.4469,
+      "num_input_tokens_seen": 9136816,
+      "step": 880
+    },
+    {
+      "epoch": 0.2614475627769572,
+      "grad_norm": 14.335926789263953,
+      "learning_rate": 9.823196130450434e-05,
+      "loss": 0.3859,
+      "num_input_tokens_seen": 9189808,
+      "step": 885
+    },
+    {
+      "epoch": 0.26292466765140327,
+      "grad_norm": 24.791700587075013,
+      "learning_rate": 9.819962800327156e-05,
+      "loss": 0.4794,
+      "num_input_tokens_seen": 9241712,
+      "step": 890
+    },
+    {
+      "epoch": 0.26440177252584934,
+      "grad_norm": 16.38282434047279,
+      "learning_rate": 9.81670071435415e-05,
+      "loss": 0.4476,
+      "num_input_tokens_seen": 9293328,
+      "step": 895
+    },
+    {
+      "epoch": 0.2658788774002954,
+      "grad_norm": 3.8069696135300846,
+      "learning_rate": 9.813409891992988e-05,
+      "loss": 0.4852,
+      "num_input_tokens_seen": 9345160,
+      "step": 900
+    },
+    {
+      "epoch": 0.2658788774002954,
+      "eval_loss": 0.5605542063713074,
+      "eval_runtime": 19.0274,
+      "eval_samples_per_second": 3.153,
+      "eval_steps_per_second": 0.788,
+      "num_input_tokens_seen": 9345160,
+      "step": 900
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 8822832,
+  "num_input_tokens_seen": 9345160,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1539,7 +1628,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 582086830587904.0,
+  "total_flos": 616551927513088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null